Web Crawling Based Context Aware Recommender Syste

Boppana and Sandhya Journal of Big Data (2021) 8:144
https://doi.org/10.1186/s40537-021-00534-7
RESEARCH Open Access
Web crawling based context aware

recommender system using optimized deep
recurrent neural network
Venugopal Boppana1* and P. Sandhya2
*Correspondence:
[email protected] Abstract
1
School of Computer Science Recommendation systems are obtaining more attention in various application fields
and Engineering, Vellore Institute
of Technology, Chennai Campus, especially e-commerce, social networks and tourism etc. The top items are recom-
Chennai, India mended based on the ability of recommender system which predict the future
Full list of author information is preference out of the available items. Because of the internet, the people in the current
available at the end of the article
society has too many options that’s why the recommendation system is very essential.
The recommendation is achieved by the particular users who predict the ratings for
numerous items and recommend those items to other users. Majorly, content and
collaborative filtering techniques are employed in typical recommendation systems to
find user preferences and provide final recommendations. But, these systems com-
monly lacks to take growing user preferences in various contextual factors. Context
aware recommendation systems consider various contextual parameters into account
and attempt to catch user preferences appropriately. The majority of the work in the
recommender system domain focuses on increasing the recommendation accuracy by
employing several proposed approaches where the main motive remains to maxi-
mize the accuracy of recommendations while ignoring other design objectives, such
as a user’s an item’s context. Therefore, in this paper an effective deep learning based
context aware recommendation model is proposed which can be act as an efficient
recommender system by showing minimum error during recommendation. Initially,
the dataset is pre-processed using Natural Language Tool Kit (NLTK) in Python platform.
After pre-processing, the TF–IDF and word embedding model is used for every pre-
processed reviews to extract the features and contextual information. The extracted
feature is considered as an input of density based clustering to group the negative,
neutral and positive sentiments of user reviews. Finally, deep recurrent neural Network
(DRNN) is employed to get the most preferable user from every cluster. The recurrent
neural network model parameter values are initialized through the fitness computa-
tion of Bald Eagle Search (BES) algorithm. The proposed model is implemented using
NYC Restaurant Rich Dataset using Python programming platform and performance is
evaluated based on the metrics of accuracy, precision, recall and compared with exist-
ing models. The proposed recommendation model achieves 99.6% accuracy which is
comparatively higher than other machine learning models.
Keywords: Context aware recommendation, Web crawling, User preference vector,
Similarity measure, Deep recurrent neural network
© The Author(s), 2021. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits
use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original
author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third
party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the mate-
rial. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or
exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://
creativecommons.org/licenses/by/4.0/.
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Boppana and Sandhya Journal of Big Data (2021) 8:144 Page 2 of 24
Introduction
Nowadays, recommendation systems (RSs) are more eminent and they are used in dif-
ferent web application areas. The recommendation system is a kind of software tool that
provides opinions to the users based on their needs also it is known as an information
filtering system. The opinions are like what to purchase, which song to heed, which book
to recite, etc. [1]. The information overloading is a difficult problem on the internet
because of the explosive growth in the count of existing data and the count of visitors
to visit a web page frequently. The common examples for the application areas of rec-
ommendation systems are recommending books in Amazon and recommending mov-
ies in Netflix [2, 3]. The internet store gets personalized for every customers through
recommendation of books from the popular website Amazon.com. Several consumers
or consumer groups benefit through different personalized ideas because many of the
recommendations are personalized also it delivered a ranked list of items. Based on that
ranking, RSs predict apt products and facilities for the users [4].
The most prominent strategies of the recommendation systems are the Content and
Collaborative filtering method, Hybrid recommendation, Knowledge-based filtering,
Demographic method and, Model-based technique. Some researchers use both the
combination of these methods for recommendation systems [5]. In the content-based
filtering, the fundamental process relies on consumer descriptions and their needed
item. Then a profile is managed representing the items by means of signifying it to the
target user who previously adored the same [6]. The Collaborative filtering method is the
most renowned method also widely used in products, services and travel recommenda-
tions [7]. This is also a common method for designing the recommendation system. It
uses a massive volume of data collected from the behaviour of the user in an earlier time
and predicts which item the users like most [8].
Hybrid recommendation approach is the combination of two or more recommenda-
tion method which is used to enhance the quality of recommendations to overcome the
restrictions of outdated recommendation methods and the best example for this method
is Netflix [9]. Knowledge-based filtering recommended the items built on either sugges-
tion related to user preferences or particular domain information regarding how items
connect to user preferences [10]. In the demographic recommender system, it offers rec-
ommendations based on a demographic profile of the user like gender, age, nationality
etc. [11]. The model-based approach is a kind of collaborated filtering technique that
involves constructing a model relevant to dataset rankings. It is known by extracting the
data from the dataset and utilize that as a model to provide recommendations also it
possibly deliver the benefits of scalability and speed [7].
Most of the recommender systems overlook the succeeding information and mainly
concentrated on the content information. Still, the successive data offers more evidence
about the behaviour of the user [12–15]. After many years, web service becomes the
standard technology for sharing software, information, and computing resources on
numerous amount of web pages. It is a process of recognizing useful services and recom-
mending those services to end users [16]. In web services, the web page recommender
is essential for websites. The knowledge representation and integrating the web are the
challenging problems to make effective web page recommendation. So many of the rec-
ommender system uses web usage and domain knowledge through the semantics [17].

The proposed recommendation model make a decision for visiting a restaurants

based on user reviews and contextual information. The convention recommender sys-
tem gives attractive and relevant recommendation for an active consumer using con-
tent based filtering algorithm, collaborative algorithm and hybrid filtering algorithm
on the basis of predicted ratings. The recent researches employed the sentiment anal-
ysis to predict the user preference based on reviews [18]. The combination of sen-
timent analysis and aspect categorization also employed for hotel Recommendation
System based on online review [19]. At any time, prediction of unseen data is possible
if the model is established by the supervised learning algorithm on available data his-
tory like user reviews and user item rating.
To achieve this, we suggested a context aware recommender system in this work.
This method is more prevalent in recent years and they play an imperative part in
intelligent choice making systems. This method provides the information related to
most visited places such as restaurants. The goal of this technique is to effectively
predict user intention and make recommendation accordingly. Moreover, investigate
the behaviour of already visited users and create recommendations based on new user
preferences. In this study, we have proposed a context aware recommendation system
considering user preference and contextual information for predicting favourite res-
taurants. The major goals of present paper are given below:
1. To build an effective clustering algorithm to analysing the user review sentiments

based on word embedding models.
2. To propose a deep recurrent neural network model for accurate recommendation
prediction by the aid of word embedding with contextual features.
3. To improve a deep recurrent neural network model using bald eagle search algo-
rithm for optimal selection of hyper parameters.
The remainder of this paper is structured as follows: the recent related works with
problem definition is provided in “Related works” section. “Proposed methodology
for graph based recommendation model” section presents the details of proposed
context aware recommendation model. “Results and discussion” section illustrates
the simulation and the performance of our proposed model, and lastly, “Conclusion”
section provides the conclusion of the paper.
Related works
Some of the recent related studies related to recommendation models is discussed
below:
A deep learning modified neural network algorithm was proposed by Sasikala and
Mary Immaculate Sheela [20] for sentiments analysis of online product review. For
forthcoming forecast of online products, a method of Improved Adaptive Neuro-Fuzzy
Inference System (IANFS) was presented. Initially, the values of dataset are divided as
collaboration based (CLB), Content-based (CB) and Grade-based (GB). Next, by utiliz-
ing DLMNN every consequence goes through review analysis (RA) as positive, neutral
and negative. For future predictions, the IANFIS performs a weighting factor.

Based on hybrid recommendation algorithm a novel implementation of a product

recommendation system was presented by Revathy [21]. Based on the original struc-
ture to deliver a visual data organization is the main advantages of this method. To
search the products anytime and anyplace this method delivers a simple method.
Sentiments, review and ratings are evaluated and characterized as negative and posi-
tive sentiments. To avoid fake reviews, the MAC based filtering method can be used.
Supermarket can help for get new customers, easy transactions and easy buying.
Hybrid References is one of the main system module which help to mitigate the issues
of content based recommendations and traditional collaborative filtering models.
By integrating online product Song et al. [22] implemented a prospect theory-based
method to rank the products. As indicated by the customers’ essential product neces-
sities of alternative products are gotten. Then, depends on multiple criteria the objec-
tive values and online scores of alternative products are collected and fused when the
standardization method was completed. At last, according to the alternative products
they get the alternative products ranking depending upon numerous models. By inte-
grating the objective and subjective information using the richer products informa-
tion was a new idea in a product information.
Based on contextual information an electronic product recommender system from
sentiment analysis was presented by Osman et al. [23]. To make the items prediction
the recommendation algorithms mostly depends upon the users rating. For recom-
mender system they present a sentiment based model using contextual information.
In electronic product recommendation by using outcomes of RMSE and MAE meas-
ures their sentiment-based contextual information model provides improved
performance.
Based on the automatic features an ensemble detection method was presented by
Hao et al. [24]. At first, the users’ behaviors are analysed to collaboratively discover
the shilling profiles from multiple views like ratings, user graph and item popular-
ity. Secondly, the stacked denoising auto encoders are used based on the data pre-
processed from several views to automatically extract the consumer features with
various corruption rates. Moreover, based on principal component analysis the fea-
tures mined from various views are effectually joined. At last, the weak classifiers are
generated according to the features extracted with various corruption rates and then
combined to detect attacks.
Wu et al. [25] presented a context aware recommender system using graph convo-
lution machine (GCM). The GCM comprises encoder, decoder and graph convolu-
tional layers, the encoder part creates an embedding vectors based on users, items
and contexts. Further, the embedding vector fed into the graph convolutional layers
to refine user and item embedding’s. The decoder part output the prediction score by
taking the embedding’s of user, item, and context interactions. Moreover, deep neu-
ral network based Neural Collaborative Filtering model is proposed by He et al. [26]
for recommendation system. Cheng et al. [27] developed an Aspect–Aware recom-
mendation system based on Latent Factor Model using rating and reviews. The rating
score is predicted by an aspect importance, which is relied on the features of targeted
items and preferences of targeted user’s. Table 1 shows the comparative analysis of
above discussed related works.

Table 1 Comparative analysis of related works

References Technique Domain Dataset Metrics Context-
awareness
Sasikala and Mary Deep learning Ecommerce Own extracted Precision, Recall, No
Immaculate Sheela modified neural product online F1-score, accuracy
[20] network (DLMNN), reviews
Adaptive Neuro-
Fuzzy Inferences
System (IANFIS)
Revathy [21] Sentiment analysis Ecommerce Own extracted Precision, Recall No
product reviews
Song et al. [22] Prospect theory Ecommerce Own extracted Ranking No
and multi criteria online data
decision making
Osman et al. [23] Sentiment analysis Electronic Amazon data RMSE and MAE Yes
Hao et al. [24] Stacked denoising Ecommerce Movie lens, Netflix, Precision, Recall No
auto encoders and Amazon data
Wu et al. [25] Graph convolution Ecommerce Yelp and Amazon Hit ratio (HR) and Yes
machine (GCM) data normalized dis-
counted cumula-
tive gain (NDCG)
He et al. [26] Neural collaborative Ecommerce Movie lens and Hit ratio (HR) and No
filtering* Pinterst normalized dis-
counted cumula-
tive gain (NDCG)
Cheng et al. [27] Aspect-aware Ecommerce Amazon and Yelp RMSE No
latent factor model data
(ALFM)
Core finding of problem and motivation

Recommender systems customized to influence contextual information during the
course of final recommendation is referred as context-aware recommender systems.
The accessible past studies explores different ways to make recommendations and
suggests various methods with respect to users’ requirements. The most of the stud-
ies in the recommender system field given attention on maximizing the accuracy of
recommendation by utilizing different methodologies where the key goal focuses to
increase the recommendation accuracy while neglecting additional major require-
ments, such as the context information related to user’s an item’s context. The prin-
cipal problem for a recommender system is to provide fruitful recommendations by
utilizing user-item contextual information.
This research paper presents a context aware recommender model by employing
by word embedding based contextual feature extraction with effective sentiment
clustering and deep learning techniques. It helps to facilitate the recommendation
of restaurants with the aid of user centric feedback reviews from online platform.
We extract the textual information’s keywords form raw web data, which reflects the
ideal way for extracting the contextual informative features. It creates information
representation model, via word embedding methods. Finally we develop an offline
knowledge building and recommendation prediction model using deep machine
learning techniques.

Proposed methodology for graph based recommendation model

Recommendation system is a data refining model, which offers users with data, which
he/she may be fascinated in. Context aware recommendation systems have fairly a deter-
mined technique in analysing users’ behaviour in the internet and harvest endorsements
based on their favourites. It helps to facilitate to recommend good services via online
media. Initially, we adopt Complex Event Processing (CEP) module in proposed recom-
mender system to process multiple streams of continuous data, and identify meaningful
attributes. The most commonly used TF–IDF and word embedding model is employed
to extract the feature from user reviews along with contextual information. The density
based clustering algorithm follows the similarity measures such as Dice’s coefficient,
Jaro–Winkler distance, Damerau–Levenshtein distance, Cosine similarity and Tversky
index for grouping the sentiments user reviews. Finally, a deep recurrent neural network
(DRNN) model is developed to select the user preference vector for final recommenda-
tion. The process flow of system model is displayed in Fig. 1.
In this paper, a model has been introduced that yields recommendations to consumers
considering the contextual details such as working time and location of restaurants given
by the consumer apart from reviews. Initially, the dataset is obtained for performing the
further process. The dataset is pre-processed by NLTK tool in Python platform. Based
on the dataset, we create the weight vector matrix based on TF–IDF model. Further,
the weight vector matrix is inputted to DRNN to predict the possible recommendation
based on user preferences. In DRNN training phase, pre-visited user feedback review
Term and word

Preprocessing embedding based
User Reviews
feature
Preprocessing and Feature extraction Phase
Cluster data points using density

Web Crawling based clustering algorithm
Deep Recurrent Neural Bald Eagle Search

Network Algorithm
Selection of preferable data points from every

cluster using DRNN model
Obtain Recommended Results
Fig. 1 Process flow diagram of graph based recommendation model

vector score is computed to make the possible recommendation. After the training
process, the new user preference vector is generated during the testing phase for final
recommendation.
Web crawling
The major intention of web crawler is to extract the information from web sources in
customized way. The usage of web crawler is not problematic when obtaining the reviews
from the web sources. It is used to save the web sheets also link them in to the local
sources because which are the central phase of search engines. In an integrated setting,
gathering and analysing the whole contents of web is the common goal of web crawlers.
In this work, Beautiful Soup based web Crawling technique is utilized for scraping the
data’s for websites [28].
Complex event processing (CEP)

On the basis of event pattern or event procedure rule, the CEP is said to be a real-time
data process methodology. It is used to retrieve the high level knowledge from the large
extent of data. It also utilized to analyse the trends, track the torrents of data from mul-
tiple sources, and patterns. In this work, PySiddhi tool is utilized to get the events from
data streams, senses complex conditions represented through a Streaming SQL lan-
guage, and generates possible actions [29].
Pre‑processing
Several websites are used to collect the data about web pages. Initially, the pre-pro-
cessing is done to the datasets. The unwanted noise in the dataset is eliminated by this
process also it have direct influence over the calculation of the output. The following dif-
ficulties are processed by the pre-processing step: (i) punctuation removal, (ii) removal
of stop words like prepositions, articles, etc. and (iii) alteration of upper case letters to
lower case letters.
Stop words removal

The English words which doesn’t give much meaning to the sentence is termed as
stop words. These meaningless words are removed without losing the meaning of the
sentence. The examples for stop words are like he, the, have, of, etc. Normalization is
described by removing the repeated words. Some words are repeated many time in the
web pages or articles. These type of letters not matched with all dictionary words and
these are very complex to deal with. For illustration, “super” can be inscribed as superrr,
sooper, or suuuppper. The proposed technique declines such occurrences through pre-
processing. The row is altered when a letter appears above two times.
Stemming
The procedure of stemming is defined by transforming all the words in a text to their
stem or root. The morphological attaches from the words are eliminated by this pro-
cess. The word is formed by stem of a word in which it is known as root. For exam-
ple, words “stems”, “stemmed”, “stemmer”, and “stemming” take a mutual stem that is
“stem”. The different forms of a words are recognized by this stemming and combine

those words form together. Without stemming process, various forms of a single word
is considered as different words. The terms are converted to their stem with the appli-
cation of certain heuristics to remove the suffixes.
During stemming process suffix words like ‘ed’, ‘ing’, ‘ly’, ‘ment’ were eliminated from
every user reviews.
Example for stemming word removal on user review:
Input: Amazing food, live entertainment. Great place!

Output: Amaz food, live entertain. Great place!
The outcome gained on stemming phase is visibly represented in above example.
Feature extraction
In recommendation system, feature extraction process plays an important role to
reduce the dimensionality of the input data to ensure the prediction accuracy and
enhance the time efficiency. In this recommendation model, related features are
extracted from the terms returned through the pre-processing phase utilizing a nor-
malized TF–IDF, and word embedding method.
Term based feature extraction

In recommendation system, feature extraction process plays an important role to
reduce the dimensionality of the input data to ensure the prediction accuracy and
enhance the time efficiency. In this recommendation model, related features are
extracted from the terms returned through the pre-processing phase utilizing a nor-
malized TF–IDF method. Normalized TF–IDF is a vector space method that simply
extracts the weight of terms numerically. Here, TF–IDF is integrated due to its highly
precise performance when compared to other statistical methods. It extracts the
features from the high level features by discarding the low level features. This merit
makes us to integrate TF–IDF in this proposed framework. Because, the taken input
is web related reviews which may contain large number of unwanted data which may
reduce the proposed performance. To avoid that, we have used TF–IDF for feature
extraction [33]. For every term i , the weight is calculated as follows:

TFi × log nNi
Wi =
n 2 , (1)
N
i=1 TF i × log ni
where ni is the number of reviews comprising term i and N is the total number of
reviews. TF represents the number of occurrence of each term in a review, while IDF
denotes the length normalization. The pseudo code for the feature extraction process is
illustrated in Algorithm 1. The related-term matrix features acquired at this stage are fed
into the fuzzy based clustering.

Feature extraction based on word embedding

One of the most popular representation of document vocabulary is known as word
embedding. The word2vect is utilized for creating the word embedding. The procedure
of the word is not understood by a machine this is the reason for using word embedding.
The numerical or binary value can be understand by machine. So, to process a language
the word2vec must be needed. Each machine can change the tokenize word to a vector
after applying word embedding.
One of the most popular technique by using shallow neural network to learn word
embedding is known as word2vec. Two methods are utilized in word2vec for word
embedding such as continuous bag of word (CBOW) and skip-gram [30]. CBOW is uti-
lized for word context to predict the target word. A word is utilized by skip gram to pre-
dict the target value.
CBOW The hidden layer is eliminated and projection shared the same position which
gotten by all words. This way of procedure is known as bag of word. On the other side its
continuously distributed words thus it named as CBOW.
The mathematical expression for CBOW method is,
Q = N × D + D × log2 (v). (2)
Skip-Gram Based on other words the skip-gram method tries to find the words in a
same sentence. We utilize the present word with hidden layer projection as an input that
may calculates the words within the range.
The formula for skip-gram method is,

Q = C × D + D × log2 (v) . (3)
where word maximum distance is represented as C .
Context information extraction based on word embedding

The contextual information of user tip is extracted to access the hidden bases of knowl-
edge leads to find out the rich context. The process of contextual feature extraction

comprises both bag of words and word embedding model to extract the simple expres-
sions from the collections of user tips and identifying the valuable expressions.
In the word embedding model, the threshold value based comparison is made to
extract the context from user tips. Mainly, the similarities among contexts also taken to
strengthen the relations among them. For a user tip T1 = {c1 = {e1 , e2 , e3 }, c2 = {e2 , e4 }},
where c1 and c2 are the contexts for the expressions e1 and e2, correspondingly. If the
value of similarity ValS1,2 = L(cL(c
1 ∩c2 )
2)
among the contexts c1 and c2 is higher than or equal
to a threshold value Tv , then the context c2 is append into the context list of the tip T1.
Likewise, If the value of similarity ValS2,1 among the contexts c2 and c1 is higher than Tv ,
then the context c2 is append into the context list of the tip T1. The setting of threshold
value Tv is user oriented to carrying out the technique.
Density based clustering

In the clustering phase, all the features extracted from user reviews are gathered into
various groups based on the similarities. Clustering is termed as an unsupervised learn-
ing process that determines the hidden patterns in the instance data; also, it is used to
identify the meaningful features for accurate recommendation. Moreover, in statisti-
cal machine learning and data mining, the process of clustering is considered as one of
the important tasks. In this work, Density based Clustering (DBC) Algorithm is used to
label the selected features into positive, neutral and negative reviews. DBC algorithm
which used to measure the values of clustering points and also it used to measure the
radius of density at minimum number of points. Since it denote the distance function as
d(p, q) and it parameters mentioned as Eps—neighbourhood points and min pts—mini-
mum number of points. The input feature set has measured at two dimension and the
dimension are measured as two point which shown in Eq. (4);
2 2 1/2
tp − tq hp − hq (4)
d(p, q) = 2
+ ,
tscale h2scale
where delta time has represents as ‘t’, Elevation has represented as ‘h’ and tscale and hscale
used for normalization method so that can able to compare the dataset points over ‘t’
and ‘h’ axis. Therefore, the d(p, q) function are unit less thus the heuristic of effective
way to determine as two parameters. Here the Eps value determine the points at all time
so it can modify only min pts because that can able to estimate the density of the average
points from search space.
The distance between the cluster centroid and the data point is evaluated to update the
cluster centroid which is performed using the different similarity calculation techniques
such as Dice coefficient, Damerau–Levenshtein distance, Tversky index, Cosine similar-
ity, and Jaro–Winkler distance [31] are defined below;
• Dice’s coefficient
This similarity measure used to estimate the similarity of user reviews, and the math-
ematical formulation for similarity estimation, which is shown in Eq. 5

2|A ∩ B|
QS = , (5)
|A| + |B|
where |A| and |B| represents the sum of expressions available in reviews. QS repre-
sents quotient of similarity.
• Cosine similarity
In this similarity method, two vectors of an inner product space is calculated to
determine cosine of the angle. Cosine of 0° value is 1, for some other angle it is
< 1. Majorly, in positive sign cosine similarity is utilized, its outcomes proficiently
limited in (0, 1). Cosine similarity [cos(θ)] can be computed using the subsequent
Eqs. 6 and 7,

Dot product (K , L)
Similarity = cos θ = , (6)
�K � ∗ �L�
n

Ki Li
i=1
cos θ = ,

n

n (7)
K2
L2 i i
i=1 i=1
where Ki and Li are constituent of vector K and L.

• Tversky index
It is an asymmetric similarity measure which is obtained by generalizing the dice
coefficient and Jaccard index.
For set, X and Y, the Tversky index lies between 0 and 1.
|X ∩ Y |
S(X, Y ) = , (8)
|X ∩ Y | + α|X − Y | + β|Y − X|
In case, if α = β = 0.5, it simplifies dice coefficient, and α = β = 1 it simplifies

Jaccard index.
• Jaro–Winkler distance
This string metric that measures the edit distance among two different sequences
are referred as Jaro–Winkler distance.
For two strings s1 and s2 , the Jaro–Winkler distance is defined in Eq. (9),

0 if m = 0
simj = 1 m , (9)

m m−t
3 |s1| + |s2| + m otherwise
where |si| represents string length, transposition number is denoted as t and the
number of matching characters are denoted as m.
• Damerau–Levenshtein distance
It is also considered as string metric which estimate the edit distance among
two different sequences. Informally, the less number of operations (like, substi-

tution, transposition, deletion, and insertion) that are required to convert one
word to another is obtained by Damerau–Levenshtein distance.
The distance exist between 2 strings a and b is defined by Damerau–Levenshtein

distance using the function da,b i, j . The value obtained using this function is the

distance between the string a having i symbol prefix and the string b of j symbol
prefix.
Recommendation prediction using deep recurrent neural network

In the DRNN based model, the user tags along with tips are needed to get the list of
restaurant venues to be recommended. In this paper, the popular restaurant venues in
Foursquare Dataset is recommended by using the deep recurrent neural network. The
check-in, tip and tag data are significant for recommending a restaurant.
The connection between the neurons in recurrent neural network (RNN) forms a
directed circle. The RNN keep track of its internal hidden state over the recurrent con-
nections which is differ from the feed forward network. The text and speech are the dif-
ferent types of task and the behaviour of RNN is suitable for processing these particular
tasks. The usage of sequential information is the idea behinds this RNN. The RNN have
the capability of predict the next word in the sentence given every single word before
that word.
The recurrent neural network architecture is illustrated in Fig. 2.
Input Layer
Review 1(text)
Hidden Layer
Review 2(text) Output Layer
x (k–1)
u (k)
Review 3(text)
y (k)
Review n(text)
uc(k)
Fig. 2 Recurrent neural network architecture of venue recommendation based on user tags and tips

DRNN based recommendation prediction

The feature extracted from TF–IDF and word2vec is adopted as an input of the DRNN in
the proposed model. Due to the different loss function, the BES considered as the popular
choice for hyper parameter tuning. The proposed RNN model has three different layer i.e.
input, output and hidden layer which is shown in Fig. 3. All the inputs and outputs are inde-
pendent of each other in traditional neural network. The RNN recursive formula is shown
below.
ht = tanh (Wh ht−1 + Wx xt ), (10)
yt = Wy ht , (11)
where weighting matrix is represented as Wh, input vector is represented as xt , hid-

den layer vector is represented as ht and output vector is represented as yt . Long term
dependencies issue is presented in RNN, the issues of weight matrix and long interval
time keeps to multiply recurrently with earlier outcomes. This may cause exploding
gradient and vanishing gradient issues. To avoid this issue, Long Short Term Memory
(LSTM) is used which will enhance the performance.
The structure of LSTM units is used in RNN layer. The RNN with LSTM units is known
as LSTM network. The variance among the traditional RNN and LSTM in which every
neuron in LSTM is a memory cell. Every neuron includes three gates such as input, forget
and output gates.
From the cell, the forget gate f (t) defines which data will be unwanted. At the previous
units t − 1 by entering the output ht−1 and add the input xt with current time t in to sig-
moid function s(t).

f (t) = σ Wf · [ht−1 , xt ] + bf , (12)
Fig. 3 Performance analysis based on Dice’s similarity coefficient

1
S(t) = , (13)
1 + e−t
where the weight matrix is represented as W and bias vector is represented as b.

The gate of input explains which new data to recollect in cell state.
i(t) = σ (Wi · [ht−1 , xt ] + bi ), (14)
C̃(t) = tanh (Wc · [ht−1 , xt ] + bc ). (15)
To get the updated information the values of i(t) and C̃(t) is multiplied by the sigmoid
function that we really want to add the cell state.
C(t) = f (t) × C(t − 1) + i(t) × C̃(t). (16)
The output gate explains which data will be output in the cell state. The cell state is first
triggered in the tanh layer before being multiplied by o(t). At time t the multiplication
result is the output data h(t) in the block of LSTM.
o(t) = σ (Wo · [ht−1 , xt ] + bo ), (17)
h(t) = o(t) × tanh (Ct ). (18)
The available data was categorized into three non-overlapping sets for the purpose of
training, testing and validation. The size of training data varies depending on the sce-
nario. At first, we want to train the LSTM model in foursquare location recommenda-
tion datasets. To choose the best parameters as well as the performance in the proposed
model the validation is employed. Finally the same dataset is utilized to the testing pur-
pose to verify the performance and accuracy. The weight and bias value of all the three
gates can be updated by BES [32] optimization. To validate the co-sequences of every
phase of hunting is the main behaviour of bald eagle. The hunting behaviour of BES can
be classified in to three stage i.e. select, search and swooping stage.
Wi (t)
Fitness f (t) = max . (19)
Wbest
In the select phase, the BES find and pick the best area as best bias within the chosen
search space.
bnew,i = bbest + α ∗ r(bmean − bi ), (20)
where random number is denoted by r.

In the search stage, the best position as best weight value for the swoop is mathemati-
cally calculated by
Wi, new = Wi + y(i) ∗ (Wi − Wi+1 ) + x(i) ∗ (Wi − Wmean ). (21)
In the swooping stage, the bald eagle swings from best weight in the search space and
best bias in the best area. Both these are calculated and mathematically illustrated as
below

W , bi, new = rand ∗ W , bbest + x1(i) ∗ (bi − c1 ∗ Pmean ) + y1(i) ∗ (Wi − c2 ∗ Wbest ).
(22)
Based on the above Eq. (23), the weight and bias value will be updated in RNN.
Model training
In this study, an end to end type of LSTM model is employed to explore the process of
recommendation prediction. The related model parameter setting is listed in Table 2.
The learning rate is initially set to 0.002, the BES optimization is employed to adjust
the hyper parameters during model training. The batch size is set to 8, and the state
and hyper parameters in the proposed model are marginally adjusted on the testing
process for correct prediction.
Table 2 Parameter setting of proposed model

Parameter Value
Number of Bi-LSTM layers 3

Input layer size 40
Hidden layer size 80
Output layer size 20
Learning rate 0.002
Batch size 8
Decay factor 0.2
Decay period 5
Optimizer BES

Results and discussion

In simulation analysis, the outcome of proposed DRNN-BES is compared with the exist-
ing KNN based collaborative filtering model and ANN, DNN, DAE, DAE-SR based
recommendation models. For validating the performance of proposed model, the data
sources are obtained from the Foursquare NYC Restaurant Rich Dataset [34]. The data
set comprises 3112 users and 3298 venues with 27,149 check-ins and 10,377 tips. For
the purpose of performance evaluation, the dataset comprising 10,377 tips is partitioned
into a ratio of 70:20:10 for training, validation, testing respectively i.e., 7264 reviews for
training, 2075 for validation, 1038 for testing. The proposed strategy is estimated by
means of accuracy, recall and precision. The proposed DRNN based recommendation
model simulated on Python programming platform. The performance analysis is made
based on the similarity measure, sentiment with context information and varying the
training size of data which are presented in upcoming sub sections.
Performance measures
The following are the performance measures that are used in the simulation for the per-
formance analysis. Accuracy, Precision and Recall and are the performance parameters
utilised in the experimental results.
• Precision value It is indicated for regained document. It is estimated through the

division of total count of related documents to total count of resultant documents.
TP
Precision = . (23)
TP + FP
• Recall value Related documents associated with the request.
TP
Recall = . (24)
TP + FN
• Accuracy value Essential related documents for classification is given by accuracy.

The accuracy performance is always in better performance.
TP + TN
Accuracy = . (25)
TP + FP + FN + TN
(TP—true positive, TN—true negative, FP—false positive, FN—false negative).
Performance analysis based on similarity measures

The performance analysis of KNN, ANN, DNN, DAE, DAE-SR and proposed DRNN-
BES for Dice’s coefficient Jaro–Winkler distance, Damerau–Levenshtein distance,
Cosine similarity and Tversky index employed in density peak clustering algorithm are
compared and explained in this section.
The Table 3 gives the performance value of KNN, ANN, DNN, DAE, DAE-SR and pro-
posed DRNN-BES for Dice’s coefficient and Fig. 3 shows the graphical representation
of analysis. For KNN, ANN, DNN, DAE, DAE-SR and proposed DRNN-BES classifier
precision value are 85.4, 88.5, 91, 89.6, 94.2 and 97.3% recall value are 80.2, 84.9, 87.9,

Table 3 Dice’s coefficient based performance comparison

Performance KNN ANN DNN DAE DAE-SR DRNN-BES
metrics
Precision 85.4 88.5 91 89.6 94.2 97.3

Recall 80.2 84.9 87.9 90.6 95.2 97.8
Accuracy 85.3 90 90.4 92 94.7 97.3
90.6, 95.2 and 97.8%. The accuracy value for DNN, ANN, KNN, DAE-SR and proposed
DRNN-BES classifier are 85.3, 90, 90.4, 92, 94.7 and 97.3%. Compared with the existing
techniques our proposed approach has better performance.
The Table 4 and Fig. 4 depicts the performance value and investigation of KNN, ANN,
DNN, DAE, DAE-SR and proposed DRNN-BES for Damerau–Levenshtein distance
based similarity. For KNN, ANN, DNN, DAE, DAE-SR and proposed DRNN-BES clas-
sifier precision value are 76.2, 79.2, 82.5, 83.8, 90.3 and 94.3%, recall value are 79.2, 80.4,
86.4, 88.2, 89.3 and 93.6% also accuracy value are 78.2, 82.4, 84.4, 86.4, 90.7 and 94%.
It is obviously agreed, compared with other classifier the proposed approach has better
performance.
The Table 5 gives the performance value of KNN, ANN, DNN, DAE, DAE-SR and
proposed DRNN-BES for Tversky index and Fig. 5 shows the graphical representation
Table 4 Damerau–Levenshtein distance based performance comparison

metrics
Precision 76.2 79.2 82.5 83.8 90.3 94.3

Recall 79.2 80.4 86.4 88.2 89.3 93.6
Accuracy 78.2 82.4 84.4 86.4 90.7 94
Fig. 4 Performance analysis based on Damerau–Levenshtein distance

Table 5 Tversky index based performance comparison

metrics
Precision 90.9 93.5 96.8 97.2 97 99.5

Recall 92.8 94.2 95.7 92.8 98.8 99.3
Accuracy 93.8 95.9 97.6 98.1 99 99.4
Fig. 5 Performance analysis based on Tversky index
Table 6 Cosine similarity based performance comparison

metrics
Precision 90 92 94 94 98.2 98.6

Recall 85 88 92 93 98.5 98.9
Accuracy 89 93 96 95 98.3 98.7
precision value are 90.9, 93.5, 96.8, 97.2, 97 and 99.5% recall value are 92.8, 94.2, 95.7,
92.8, 98.8 and 99.3. The accuracy value for DNN, ANN, KNN, DAE-SR and proposed
DRNN-BES classifier are 93.8, 95.9, 97.6, 98.1, 99 and 99.4%. Compared with the
existing techniques our proposed approach has better performance.
The Table 6 and Fig. 6 depicts the performance value and investigation of KNN,
ANN, DNN, DAE, DAE-SR and proposed DRNN-BES for Cosine similarity. For KNN,
ANN, DNN, DAE, DAE-SR and proposed DRNN-BES classifier precision value are
90, 92, 94, 94, 98.2 and 98.6%, recall value are 85, 88, 92, 93, 98.5 and 98.9% also accu-
racy value are 89, 93, 96, 95, 98.3 and 98.7%. It is obviously agreed, compared with
other classifier the proposed approach has better performance.

Fig. 6 Performance analysis based on cosine similarity
Table 7 Jaro–Winkler distance based performance comparison

metrics
Precision 79.2 80.2 88.4 87.3 91.4 95.7

Recall 80.3 83.6 85.9 88.2 90.3 95.8
Accuracy 81.2 85.5 87.2 90.3 93.6 95.8
Fig. 7 Performance analysis based on Jaro–Winkler distance

Table 8 Evaluation of accuracy using various feature representations

Size of training data Feature representation DNN DAE-SR DAE DRNN
Complete (100%) TF–IDF 92.5 93.2 94.6 95.2

TF–IDF + CBOW 95.2 96.8 97.5 98.3
TF–IDF + CBOW + Skip-gram 96 97.3 98.4 99.5
80% TF–IDF 91.3 92.7 93 94.3
TF–IDF + CBOW 92.8 94 95.8 97.6
TF–IDF + CBOW + Skip-gram 95.2 96.2 97.2 98.2
60% TF–IDF 90.2 91.3 92.1 93.2
TF–IDF + CBOW 92.3 93 94.2 95.8
TF–IDF + CBOW + Skip-gram 93 94.3 95.4 97.2
40% TF–IDF 90.2 90.8 91.4 92
TF–IDF + CBOW 91.3 92.2 93.6 94.8
TF–IDF + CBOW + Skip-gram 93.5 94.6 95.8 96
Table 9 Evaluation of accuracy using various sentiment with context information

Sentiment Context DNN DAE-SR DAE DRNN
Negative Without context information 90.5 92.2 93.6 94.2

With context information 91.2 92.8 94.5 95.3
Neutral Without context information 93.3 93.7 95 96.3
With context information 94.8 94 96.8 97.8
Positive Without context information 95.2 96.3 97.1 98.2
With context information 96.3 97.4 98.5 99.6
The Table 7 gives the performance value of KNN, ANN, DNN, DAE, DAE-SR and
proposed DRNN-BES for Tversky index and Fig. 7 shows the graphical representation
precision value are 79.2, 80.2, 88.4, 87.3, 91.4 and 95.7% recall value are 80.3, 83.6, 85.9,
88.2, 90.3 and 95.8%. The accuracy value for DNN, ANN, KNN, DAE-SR and proposed
DRNN-BES classifier are 81.2, 85.5, 87.2, 90.3, 93.6 and 95.8%. Compared with the exist-
ing techniques our proposed approach has better performance. From the above results,
Tversky index based performance are is high when compared tom the other similarity.
Performance evaluation based on sentiment contextual information and training data size
In context aware recommendation models, training data size gains the notable importance.
Simulations have been conducted with different training data size. The efficiency of pro-
posed recommendation model gets increases while increasing the size of training data.
Table 8 displays the performance of proposed DRNN along with DAE-SR and DAE using
different feature representations on changing the size training data. Here firstly, a complete
training data (100% of the total data) is utilized for model training by different feature rep-
resentations. Additionally, 20% trimming is performed to each of the training data files and
recurrent the same simulations. The evaluation obtained from the table values shows that
the proposed DRNN model achieves higher accuracy up to 99.5% compared to DAE-SR
and DAE based model. Table 9 shows the accuracy performance comparison using various

sentiment with context information. From the analysis of table values conclude that the
accuracy performance is improved while adding the contextual information. Moreover, the
comparison is made with respect to training, validation, testing accuracies among the pro-
posed DRNN model with other models is displayed in Table 10.
As in our proposed model, the Cosine similarity is employed to determine the contex-
tual similarity of terms which leads to provide fair recommendation. Moreover, the pro-
posed DRNN has hybrid with BES, an optimization algorithm. This hybrid architecture has
improved the overall performance of proposed architecture. Normally, different optimiza-
tion algorithms are now available but we have selected this algorithm to hybrid with BES
this is because the proposed BES has attained efficient solution identification that other
optimization algorithms. Due to this reason, we have hybrid BES with DRNN and attained
efficient result than other existing algorithms. Existing model does not include any optimi-
zation algorithms for optimal parameter selection, but in our work we have combined BES
with DRNN to develop efficient recommendation system.
ANOVA test for statistical validation of proposed model

The DRNN based proposed recommendation model is qualitatively validated by accuracy
and recall measures which are opposed each other. The statistical implication of DRNN
model is examined using familiar statistical validation technique named as analysis of vari-
ance (ANOVA) model is employed. The result of the ANOVA test is evaluated with DAE
and DAE-SR based recommendation model to reveal the statistical implication of DRNN
model using the input metrics of accuracy and recall. Generally, the null hypothesis (Hnull)
of an ANOVA test denotes that the mean value of two or more methods for the designated
set of values are identical and so disapprove the null hypothesis assumption. The f-statistic
measure is employed to provide the outcome of an ANOVA test. After fulfilling the condi-
tion of two assumptions discussed below, the Hnull becomes disapproved.
i. The p-value < level of importance.

ii. Value of F-statistic value > value of F-critical.
Similarly, the alternative hypothesis represented as Halt defined in Eqn. 26 to pledge the
null hypothesis Hnull.
Hnull: µDRNN = µDAE − SR = µDAE, (26)
Halt: µDRNN �= µDAE − SR � = µDAE. (27)
Table 10 Evaluation of accuracy with respect to training, validation and testing

Model Training Validation Testing
DNN 94.5 90.2 96

DAE-SR 96.2 92.8 97.3
DAE 97 94.3 98.4
DRNN 99.6 95.2 99.5

Table 11 Summary of input/output values based on accuracy

(a) Summary of input values based on accuracy
Methods Trials (N) Mean Std. Dev. Std. Error
DRNN 5 0.34 0.1294 0.0579

DAE-SR 5 3 0.7906 0.3536
DAE 5 3.18 0.2864 0.1281
(b) Summary of output values based on accuracy
Source Degree of Sum of squares Mean square
freedom
Among groups 2 25.2893 12.6447

Within groups 12 2.8953 0.2413
Total 14 28.1846
Table 12 Summary of input/output values based on Recall

(a) Summary of input values based on Recall
Models Trials (N) Mean Std. Dev. Std. Error
DRNN 5 97.05 0.7984 0.3571

DAE-SR 5 94.5 0.3953 0.1768
DAE 5 92.6 0.5184 0.2318
(b) Summary of output values based on Recall
Source Degree of Sum of squares Mean square
freedom
Among groups 2 49.8583 24.9292

Within groups 12 4.2498 0.3541
Total 14 54.1081
Especially, five trails has been taken from all models by employing number of itera-
tions to conduct an ANOVA test. Additionally, other measures such as level of impor-
tance α = 0.05 and confidence interval (CI) range = 95% are considered. Tables 11(a),
(b), and 12(a), (b) have display the input selected for executing the ANOVA test based
on accuracy and recall metrics to examine the output value in the form of f-ratio and
p-value. The valuation of the test outcomes shown in Tables 11(b), 12(b), it can be con-
firmed that the alteration in the mean value of error has statistically valid, therefore the
null hypothesis Hnull is disapproved and approved the alternative hypothesis Halt . Addi-
tionally, in the ANOVA test for accuracy, the value of f-ratio is 52.4082. The p-value is 0.
Therefore, the ANOVA test outcome at p < 0.05 is valid.
The f-ratio is 52.4082. The p-value is 0. The outcome at p < 0.05 is valid.
The f-ratio is 70.392. The p-value is 0. The outcome is not-valid at p < 0.05.
Conclusion
In this paper, an effective context aware recommendation model is proposed. Initially,
the consumer feedback comments are extracted from the online amenities via web
crawling technique. In the beginning of the recommendation system, pre-processing is

carried out to remove the irrelevant words from the user reviews. After pre-process-
ing, TF–IDF vector model is employed to extract relevant features numerically from the
feedback user tips. Further, word embedding model is employed to extract the contex-
tual information from user tips. Then, the density based clustering algorithm is executed
to group similar sentiments of user tips. Finally, the deep recurrent neural network
model is employed to select the possible user preference vectors from clusters. The com-
parative analysis performed based on similarity measures, training data size and senti-
ment based contextual information using this metrics the metrics of accuracy, precision,
recall. Our proposed model achieves accuracy up to 99.6 with the inclusion of contex-
tual information and outperforms compared to other deep learning model. In future,
the aspect based opinions need to be considered to achieve fair recommendation with
different domain datasets.
Abbreviations
NLTK: Natural Language Tool Kit; TF–IDF: Term Frequency–Inverse Document Frequency; RS: Recommendation systems;
IANFS: Improved Adaptive Neuro-Fuzzy Inference System; CLB: Collaboration based; CB: Content-based; GB: Grade-
based; DLMNN: Deep learning modified neural network; RA: Review analysis; CEP: Complex Event Processing; RNN:
Recurrent neural network; LSTM: Long Short Term Memory; KNN: K-nearest neighbours; ANN: Artificial neural networks;
DNN: Deep neural network; DAE: Denoising Auto encoder; DAE-SR: Denoising Auto encoder-Super Resolution; TP: True
positive; TN: True negative; FP: False positive; FN: False negative.
Acknowledgements
Not applicable.
Authors’ contributions
VB has found the proposed algorithms and obtained the datasets for the research and explored different methods
discussed. SP contributed to the modification of study objectives and framework. Their rich experience was instrumental
in improving our work. All authors contributed to the editing and proofreading. Both authors read and approved the
final manuscript.
Funding
Authors did not receive any funding for this study.
Availability of data and materials

We have collected NYC Restaurant Rich datasets which is available publicly.
Declarations
Ethics approval and consent to participate
Not applicable.
Consent for publication

Not applicable.
Competing interests
The authors declare that they have no competing interests.
Author details
1
School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India. 2 School
of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India.
Received: 15 June 2021 Accepted: 31 October 2021
References
1. Thorat PB, Goudar RM, Barve S. Survey on collaborative filtering, content-based filtering and hybrid recommenda-
tion system. Int J Comput Appl. 2015;110(4):31–6.
2. Isinkaye FO, Folajimi YO, Ojokoh BA. Recommendation systems: principles, methods and evaluation. Egypt Inform J.
2015;16(3):261–73.
3. Tarus JK, Niu Z, Yousif A. A hybrid knowledge-based recommender system for e-learning based on ontology and
sequential pattern mining. Future Gener Comput Syst. 2017;72:37–48.

4. Ricci F, Rokach L, Shapira B. Recommender systems: introduction and challenges. In: Recommender systems hand-
book. New York: Springer; 2015. p. 1–34.
5. Chen L, Chen G, Wang F. Recommender systems based on user reviews: the state of the art. User Model User Adapt
Interact. 2015;25(2):99–154.
6. De Gemmis M, Lops P, Musto C, Narducci F, Semeraro G. Semantics-aware content-based recommender systems. In:
Recommender systems handbook. New York: Springer; 2015. p. 119–59.
7. Jiang S, Qian X, Shen J, Fu Y, Mei T. Author topic model-based collaborative filtering for personalized POI recommen-
dations. IEEE Trans Multimed. 2015;17(6):907–18.
8. Wei J, He J, Chen K, Zhou Y, Tang Z. Collaborative filtering and deep learning based recommendation system for
cold start items. Expert Syst Appl. 2017;69:29–39.
9. Al-Hassan M, Lu H, Lu J. A semantic enhanced hybrid recommendation approach: a case study of e-Government
tourism service recommendation system. Decis Support Syst. 2015;72:97–109.
10. Colombo-Mendoza LO, Valencia-García R, Rodríguez-González A, Alor-Hernández G, Samper-Zapater JJ. Recom-
Metz: a context-aware knowledge-based mobile recommender system for movie showtimes. Expert Syst Appl.
2015;42(3):1202–22.
11. Al-Shamri MY. User profiling approaches for demographic recommender systems. Knowl Based Syst.
2016;100:175–87.
12. Amara S, Subramanian RR. Collaborating personalized recommender system and content-based recommender sys-
tem using TextCorpus. In: 2020 6th international conference on advanced computing and communication systems
(ICACCS). IEEE. p. 105–9.
13. Choudhury SS, Mohanty SN, Jagadev AK. Multimodal trust based recommender system with machine learning
approaches for movie recommendation. Int J Inf Technol. 2021;13(2):475–82.
14. Wang D, Liang Y, Xu D, Feng X, Guan R. A content-based recommender system for computer science publications.
Knowl Based Syst. 2018;1(157):1–9.
15. He R, Li Q, Ai B, Geng YL, Molisch AF, Kristem V, Zhong Z, Yu J. A kernel-power-density-based algorithm for channel
multipath components clustering. IEEE Trans Wirel Commun. 2017;16(11):7138–51.
16. Yao L, Sheng QZ, Ngu AH, Yu J, Segev A. Unified collaborative and content-based web service recommendation.
IEEE Trans Serv Comput. 2015;8(3):453–66.
17. Hu Y, Peng Q, Hu X, Yang R. Time aware and data sparsity tolerant web service recommendation based on improved
collaborative filtering. IEEE Trans Serv Comput. 2015;8(5):782–94.
18. Asani E, Vahdat-Nejad H, Sadri J. Restaurant recommender system based on sentiment analysis. Mach Learn Appl.
2021;6:100114.
19. Ray B, Garain A, Sarkar R. An ensemble-based hotel recommender system using sentiment analysis and aspect
categorization of hotel reviews. Appl Soft Comput. 2021;98:106935.
20. Sasikala P, Mary Immaculate Sheela L. Sentiment analysis of online product reviews using DLMNN and future predic-
tion of online product using IANFIS. J Big Data. 2020;7:1–20.
21. Revathy R. A hybrid approach for product reviews using sentiment analysis. Adalya J. 2020;9(2):340–3.
22. Song Y, Li G, Ergu D. Recommending products by fusing online product scores and objective information based on
prospect theory. IEEE Access. 2020;8:58995–9006.
23. Osman NA, Noah SAM, Darwich M. Contextual sentiment based recommender system to provide recommendation
in the electronic products domain. Int J Mach Learn Comput. 2019;9(4):425–31.
24. Hao Y, Zhang F, Wang J, Zhao Q, Cao J. Detecting shilling attacks with automatic features from multiple views. Secur
Commun Netw. 2019. https://doi.org/10.1155/2019/6523183.
25. Wu J, He X, Wang X, Wang Q, Chen W, Lian J, Xie X. Graph convolution machine for context-aware recommender
system. arXiv preprint arXiv:2001.11402. 2020.
26. He X, Liao L, Zhang H, Nie L, Hu X, Chua TS. Neural collaborative filtering. In: Proceedings of the 26th international
conference on World Wide Web. 2017. p. 173–82.
27. Cheng Z, Ding Y, Zhu L, Kankanhalli M. Aspect-aware latent factor model: Rating prediction with ratings and
reviews. In: Proceedings of the 2018 World Wide Web conference. 2018. p. 639–48.
28. Zheng C, He G, Peng Z. A study of web information extraction technology based on beautiful soup. J Comput.
2015;10(6):381–7.
29. https://siddhi-io.github.io/PySiddhi/.
30. Deepak G, Shwetha BN, Pushpa CN, Thriveni J, Venugopal KR. A hybridized semantic trust-based framework for
personalized web page recommendation. Int J Comput Appl. 2018;14:1–1.
31. Wu C, Wu J, Luo C, Wu Q, Liu C, Wu Y, Yang F. Recommendation algorithm based on user score probability and
project type. EURASIP J Wirel Commun Netw. 2019;2019(1):80.
32. Alsattar HA, Zaidan AA, Zaidan BB. Novel meta-heuristic bald eagle search optimisation algorithm. Artif Intell Rev.
2020;53(3):2237–64.
33. Garg S. Drug recommendation system based on sentiment analysis of drug reviews using machine learning. In:
2021 11th international conference on cloud computing, data science & engineering (confluence). IEEE; 2021. p.
175–181.
34. https://sites.google.com/site/yangdingqi/home/foursquare-dataset.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Terms and Conditions
Springer Nature journal content, brought to you courtesy of Springer Nature Customer Service Center GmbH (“Springer Nature”).
Springer Nature supports a reasonable amount of sharing of research papers by authors, subscribers and authorised users (“Users”), for small-
scale personal, non-commercial use provided that all copyright, trade and service marks and other proprietary notices are maintained. By
accessing, sharing, receiving or otherwise using the Springer Nature journal content you agree to these terms of use (“Terms”). For these
purposes, Springer Nature considers academic use (by researchers and students) to be non-commercial.
These Terms are supplementary and will apply in addition to any applicable website terms and conditions, a relevant site licence or a personal
subscription. These Terms will prevail over any conflict or ambiguity with regards to the relevant terms, a site licence or a personal subscription
(to the extent of the conflict or ambiguity only). For Creative Commons-licensed articles, the terms of the Creative Commons license used will
apply.
We collect and use personal data to provide access to the Springer Nature journal content. We may also use these personal data internally within
ResearchGate and Springer Nature and as agreed share it, in an anonymised way, for purposes of tracking, analysis and reporting. We will not
otherwise disclose your personal data outside the ResearchGate or the Springer Nature group of companies unless we have your permission as
detailed in the Privacy Policy.
While Users may use the Springer Nature journal content for small scale, personal non-commercial use, it is important to note that Users may
not:
1. use such content for the purpose of providing other users with access on a regular or large scale basis or as a means to circumvent access
control;
2. use such content where to do so would be considered a criminal or statutory offence in any jurisdiction, or gives rise to civil liability, or is
otherwise unlawful;
3. falsely or misleadingly imply or suggest endorsement, approval , sponsorship, or association unless explicitly agreed to by Springer Nature in
writing;
4. use bots or other automated methods to access the content or redirect messages
5. override any security feature or exclusionary protocol; or
6. share the content in order to create substitute for Springer Nature products or services or a systematic database of Springer Nature journal
content.
In line with the restriction against commercial use, Springer Nature does not permit the creation of a product or service that creates revenue,
royalties, rent or income from our content or its inclusion as part of a paid for service or for other commercial gain. Springer Nature journal
content cannot be used for inter-library loans and librarians may not upload Springer Nature journal content on a large scale into their, or any
other, institutional repository.
These terms of use are reviewed regularly and may be amended at any time. Springer Nature is not obligated to publish any information or
content on this website and may remove it or features or functionality at our sole discretion, at any time with or without notice. Springer Nature
may revoke this licence to you at any time and remove access to any copies of the Springer Nature journal content which have been saved.
To the fullest extent permitted by law, Springer Nature makes no warranties, representations or guarantees to Users, either express or implied
with respect to the Springer nature journal content and all parties disclaim and waive any implied warranties or warranties imposed by law,
including merchantability or fitness for any particular purpose.
Please note that these rights do not automatically extend to content, data or other material published by Springer Nature that may be licensed
from third parties.
If you would like to use or distribute our Springer Nature journal content to a wider audience or on a regular basis or in any other manner not
expressly permitted by these Terms, please contact Springer Nature at
[email protected]

Web Crawling Based Context Aware Recommender Syste

Uploaded by

Copyright:

Available Formats

Web Crawling Based Context Aware Recommender Syste

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Web Crawling Based Context Aware Recommender Syste

Uploaded by

Copyright:

Available Formats

Boppana and Sandhya ﻿Journal of Big Data (2021) 8:144

RESEARCH Open Access

Web crawling based context aware

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

The proposed recommendation model make a decision for visiting a restaurants

1. To build an effective clustering algorithm to analysing the user review sentiments

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Based on hybrid recommendation algorithm a novel implementation of a product

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Table 1 Comparative analysis of related works

Core finding of problem and motivation

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Proposed methodology for graph based recommendation model

Term and word

Preprocessing and Feature extraction Phase

Cluster data points using density

Deep Recurrent Neural Bald Eagle Search

Selection of preferable data points from every

Obtain Recommended Results

Fig. 1 Process flow diagram of graph based recommendation model

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Complex event processing (CEP)

Stop words removal

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Input: Amazing food, live entertainment. Great place!

The outcome gained on stemming phase is visibly represented in above example.

Term based feature extraction

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Feature extraction based on word embedding

Q = N × D + D × log2 (v). (2)

where word maximum distance is represented as C .

Context information extraction based on word embedding

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Density based clustering

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

where Ki and Li are constituent of vector K and L.

In case, if α = β = 0.5, it simplifies dice coefficient, and α = β = 1 it simplifies

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

The distance exist between 2 strings a and b is defined by Damerau–Levenshtein

Recommendation prediction using deep recurrent neural network

Review 2(text) Output Layer

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

DRNN based recommendation prediction

ht = tanh (Wh ht−1 + Wx xt ), (10)

where weighting matrix is represented as Wh, input vector is represented as xt , hid-

Fig. 3 Performance analysis based on Dice’s similarity coefficient

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

where the weight matrix is represented as W and bias vector is represented as b.

i(t) = σ (Wi · [ht−1 , xt ] + bi ), (14)

C̃(t) = tanh (Wc · [ht−1 , xt ] + bc ). (15)

C(t) = f (t) × C(t − 1) + i(t) × C̃(t). (16)

o(t) = σ (Wo · [ht−1 , xt ] + bo ), (17)

h(t) = o(t) × tanh (Ct ). (18)

bnew,i = bbest + α ∗ r(bmean − bi ), (20)

where random number is denoted by r.

Wi, new = Wi + y(i) ∗ (Wi − Wi+1 ) + x(i) ∗ (Wi − Wmean ). (21)

Content courtesy of Springer Nature, terms of use apply. Rights reserved.

Table 2 Parameter setting of proposed model

Number of Bi-LSTM layers 3

Boppana and Sandhya Journal of Big Data (2021) 8:144