Information Extraction

The increasing popularity of the social networking service, Twitter, has made it more involved in day-to-day communications, strengthening social relationships and information dissemination. Conversations on Twitter are now being explored as indicators within early warning systems to alert of imminent natural disasters such earthquakes and aid prompt emergency responses to crime. Producers are privileged to have limitless access to market perception from consumer comments on social media and microblogs. Targeted advertising can be made more effective based on user profile information such as demography, interests and location. While these applications have proven beneficial, the ability to effectively infer the location of Twitter users has even more immense value. However, accurately identifying where a message originated from or author's location remains a challenge thus essentially driving research in that regard. In this paper, we survey a range of techniques applied to infer the location of Twitter users from inception to state-of-the-art. We find significant improvements over time in the granularity levels and better accuracy with results driven by refinements to algorithms and inclusion of more spatial features.

Natural Language Processing is a programmed approach to analyze text that is based on both a set of theories and a set of technologies. This forum aims to bring together researchers who have designed and build software that will analyze, understand, and generate languages that humans use naturally to address computers.

Use of InSAR techniques in the study of unstable slopes has been suggested in recent works. However, in the ease of mass movements, which typically occur in high-relief terrain and are of limited areal extent, the detection of ground surface deformation is difficult. Moreover, the presence of vegetation cover and atmospheric effects introduces coherence loss and resolution problems in the analysis of interferometric pairs. Thus, extreme care must be taken in every step of interferometric SAR processing in order to obtain results that can be easily interpreted and be of practical utility in landslide hazard studies. The authors present the results of the application of InSAR and DInSAR techniques to a landslide test area located in the Southern Apennines. A number of SAR images was selected, whose dates coincide with periods of mass movement activity documented by in situ controls. DInSAR processing was conducted in order to assess the potential of satellite radar data for landslide monitoring. Coarse resolution is an important limiting factor for effective information extraction. Advanced processing approaches may help to overcome this limit

In this article we describe the joint effort of experts in linguistics, information extraction and risk assessment to integrate EventSpotter, an automatic event extraction engine, into ADAC, an automated early warning system. By detecting as early as possible weak signals of emerging risks ADAC provides a dynamic synthetic picture of situations involving risk. The ADAC system calculates risk on the basis of fuzzy logic rules operated on a template graph whose leaves are event types. EventSpotter is based on a general purpose natural language dependency parser, XIP, enhanced with domain-specific lexical resources (Lexicon-Grammar). Its role is to automatically feed the leaves with input data.

It is a fascinating subject to explore how well we can understand the processes of life on the basis of fundamental laws of physics. It is emphasised that viewing biological processes as manipulation of information extracts their essential features. This information processing can be analysed using well-known methods of computer science. The lowest level of biological information processing, involving DNA and proteins, is the easiest one to link to physical properties. Physical underpinnings of the genetic information that could have led to the universal language of 4 nucleotide bases and 20 amino acids are pointed out. Generalisations of Boolean logic, especially features of quantum dynamics, play a crucial role.

In this paper, a novel approach for building synopses is proposed by using a service and message-oriented architecture. The Sain-tEtiQ summarization system initially designed for very large stored databases, by its intrinsic features, is capable of dealing with the requirements inherent to the data stream environment. Its incremental maintenance of the output summaries and its scalability allows it to be a serious challenger to existing techniques. The resulting summaries present on the one hand the incoming data in a less precise form but is still on the other hand very informative on the actual content. We expose a novel way of exploiting this semantically rich information for query answering with an approach midway between blunt query answering and midway between data mining.

Investors, before making an investment decision, rely on many sources of information, including the Web, which in current times has become an important mean of mass production and dissemination of information for the financial/stock market. In this work, we study techniques of Opinion Mining, applied to investment analysis, based on news sources disseminated on the Web, in order to achieve a better consumption and processing of this information, extracting the relevant part of the huge amount of unstructured data (text) generated on the Web.

Official travel warnings published regularly in the internet by the ministries for foreign affairs of France, Germany, and the UK provide a useful resource for assessing the risks associated with travelling to some countries. The shallow IE system SProUT has been extended to meet the specific needs of delivering a language-neutral output for English, French, or German input texts. A shared type hierarchy, a feature-enhanced gazetteer resource, and generic techniques of merging chunk analyses into larger pieces are major reusable results of this work.

The evaluation of the quality of ontological classification is an important part of semantic web technology. Because this area is under constant development, it requires improvement and standardisation. This paper discusses existing evaluation metrics, and proposes a new method for evaluating the ontology population task, which is general enough to be used in a variety of situations, yet more precise than many current metrics. The paper further describes our first efforts in operationalising the evaluation procedure, including the creation of a semantically annotated corpus that will function as a test bed for the proposed evaluation mechanism, and comparison of different evaluation metrics. We conclude that for ontology-based evaluation, a more complex mechanism than is traditionally used is preferable. This mechanism aims to drive a benchmarking assessment tool for the current state-of-the-art of ontology population, and to set a standard for best practice for future evaluation of human language technology for the semantic web.

Periodicity mining is used for predicting trends in time series data. Discovering the rate at which the time series is periodic has always been an obstacle for fully automated periodicity mining. Existing periodicity mining algorithms assume that the periodicity rate (or simply the period) is user-specified. This assumption is a considerable limitation, especially in time series data where the period is not known a priori. In this paper, we address the problem of detecting the periodicity rate of a time series database. Two types of periodicities are defined, and a scalable, computationally efficient algorithm is proposed for each type. The algorithms perform in Oðn log nÞ time for a time series of length n. Moreover, the proposed algorithms are extended in order to discover the periodic patterns of unknown periods at the same time without affecting the time complexity. Experimental results show that the proposed algorithms are highly accurate with respect to the discovered periodicity rates and periodic patterns. Real-data experiments demonstrate the practicality of the discovered periodic patterns.

This paper presents the insights gained from the use of data mining and multivariate statistical techniques to identify important factors associated with a country's competitiveness and the development of knowledge discovery in databases (KDD) models to predict it. In addition to stepwise regression and weighted non-linear programming techniques, intelligent learning techniques (artificial neural networks), and inferential techniques (classification and regression trees), were applied to a dataset of 43 countries from the World Competitiveness Yearbook (WCY). The dataset included 55 variables on economic, internationalization, governmental, financial, infrastructure, management, science and technology, as well as demographic and cultural characteristics. Exploratory data analysis and parameter calibration of the intelligent method architectures preceded the development and evaluation of reasonably accurate models (mean absolute error <5.5%), and subsequent out-of-sample validations. The strengths and weaknesses of each of the KDD techniques were assessed, along with their relative performance and the primary input variables influencing a country's competitiveness. Our analysis reveals that the primary drivers of competitiveness are lower country risk rating and higher computer usage, in entrepreneurial urbanized societies with less male dominance and basic infrastructure, with higher gross domestic investment, savings and private consumption, more imports of goods and services than exports, increased purchase power parity GDP, larger and more productive but not less expensive labor force, and higher R&D expenditures. Without diminishing the role and importance of WCY reports, our approach can be useful to estimate the competitiveness of many countries not included in WCY, while our findings may benefit policy makers and international agencies to expand their own abilities, insights and establish priorities for improving country competitiveness.

Malicious executables are programs designed to infiltrate or damage a computer system without the owner's consent, which have become a serious threat to the security of computer systems. There is an urgent need for effective techniques to detect polymorphic, metamorphic and previously unseen malicious executables of which detection fails in most of the commercial anti-virus software. In this paper, we develop interpretable string based malware detection system (SBMDS), which is based on interpretable string analysis and uses support vector machine (SVM) ensemble with Bagging to classify the file samples and predict the exact types of the malware. Interpretable strings contain both application

The first object of this study is to consider ground surface displacements that occurred due to Philippine Sea Plate movements in the adjacent area of Huatung Valley in Taiwan. In order to clarify the activity of Crustal Deformation in this area, we have previously performed repeat-pass Differential SAR Interferometry (D-InSAR) to estimate and then evaluate the displacement values by geodesic levering measurements. According to these previous results using successful ENVISAT/ASAR data. The displacement values ranged between -1.5 cm and +2.8 cm, which coincide on the active fault area. In order to confirm these obtained results, we are expecting to acquire and more detail processing of L-band ALOS/PALSAR interferograms. The second object of this study is aiming to apply the Triherence method developed by ENVISAT/ASAR data to generate the stable phase points to extract the small hazardous area of landslides. According to previous results, varying of stable phase point number that indi...

Most information extraction systems focus on the textual content of the documents. They treat documents as sequences of words, disregarding the physical and typographical layout of the information. While this strategy helps in focusing the extraction process on the key semantic content of the document, much valuable information can also be derived form the document physical appearance. Often, fonts, physical positioning and other graphical characteristics are used to provide additional context to the information. This information is lost with pure-text analysis.

The rapidly increasing use of large-scale data on the Web makes named entity disambiguation become one of the main challenges to research in Information Extraction and development of Semantic Web. This paper presents a novel method for detecting proper names in a text and linking them to the right entities in Wikipedia. The method is hybrid, containing two phases of which the first one utilizes some heuristics and patterns to narrow down the candidates, and the second one employs the vector space model to rank the ambiguous cases to choose the right candidate. The novelty is that the disambiguation process is incremental and includes several rounds that filter the candidates, by exploiting previously identified entities and extending the text by those entity attributes every time they are successfully resolved in a round. We test the performance of the proposed method in disambiguation of names of people, locations and organizations in texts of the news domain. The experiment results show that our approach achieves high accuracy and can be used to construct a robust named entity disambiguation system.

Interest in information extraction from the biomedical literature is motivated by the need to speed up the creation of structured databases representing the latest scientific knowledge about specific objects, such as proteins and genes. This paper addresses the issue of a lack of standard definition of the problem of protein name tagging. We describe the lessons learned in developing a set of guidelines and present the first set of inter-coder results, viewed as an upper bound on system performance. Problems coders face include: ...

An automatic method for generating assembly instructions using CAD files is presented in this paper. Algorithms for extracting geometrical information of objects stored in a non-proprietary format, ISO-10303, STEP-CAD data file are explained. The developed algorithms form an important link between design and manufacturing. In our previous work, we designed a hierarchical assembly model that allows designers to evaluate products for manufacturing cost using a structured assembly coding system (SACS). Each SACS code represents a sequence of assembling/disassembling operations for mating two parts. The developed algorithms in this paper will generate the required SACS codes based on the geometrical and topological information extracted from the STEP files of a product in a CAD environment. Based on the generated SACS codes, the proper assembly operations can then be derived for assembling the designed product. An example of assembly with simple parts is presented to verify the method.

A ground-level semantic map is obtained by a mobile robot equipped with an omnidirectional camera, differential GPS and a laser range finder. The mobile robot uses a virtual sensor for building detection (based on omnidirectional images) to compute the ground-level semantic map, which indicates the probability of the cells being occupied by the wall of a building. These wall estimates from a ground perspective are then matched with edges detected in an aerial image. The result is used to direct a region-and boundary-based segmentation algorithm for building detection in the aerial image. This approach addresses two difficulties simultaneously: 1) the range limitation of mobile robot sensors and 2) the difficulty of detecting buildings in monocular aerial images. With the suggested method building outlines can be detected faster than the mobile robot can explore the area by itself, giving the robot an ability to "see" around corners. At the same time, the approach can compensate for the absence of elevation data in segmentation of aerial images. Our experiments demonstrate that ground-level semantic information (wall estimates) allows to focus the segmentation of the aerial image to find buildings and produce a ground-level semantic map that covers a larger area than can be built using the onboard sensors.

The paper provides an OWL ontology for legal cases with an instantiation of the legal case Popov v. Hayashi. The ontology makes explicit the conceptual knowledge of the legal case domain, supports reasoning about the domain, and can be used to annotate the text of cases, which in turn can be used to populate the ontology. A populated ontology is a case base which can be used for information retrieval, information extraction, and case based reasoning. The ontology contains not only elements of indexing the case (e.g. the parties, jurisdiction, and date), but as well elements used to reason to a decision such as argument schemes and the components input to the schemes. We use the Protégé ontology editor and knowledge acquisition system, current guidelines for ontology development, and tools for visual and linguistic presentation of the ontology. 1

This paper illustrates a system designed to automatically extract semantic annotations of the normative modifications present in legal texts. The work relies on a deep parsing approach. The problem of semantically annotating legal texts is cast to the problem of mapping parse trees to semantic frames representing such modifications. We report a preliminary experimentation along with the dataset employed, and discuss the results to point out future improvements.

This paper presents a set of tools that were developed in order to facilitate and speed up the process of building information extraction and retrieval systems for documents that exhibit a set of predefined characteristics. Specifically, the work presents a simple framework for extracting information found in publications or documents that are issued in large volumes and which cover similar concepts or issues within a given domain. The paper presents a simple model for defining background knowledge and for using that to automatically augment segments of input documents with metadata in order to assist users in easily locating information within these documents through a structured front end. The model presented makes use of both document structure as well as dynamically acquired background knowledge to achieve its goals.

Currently health care industry is undergoing a huge expansion in different aspects. Advances in Clinical Informatics (CI) are an important part of this expansion process. One of the goals of CI is to apply Information Technology for better patient care service provision through two major applications namely electronic health care data management and information extraction from medical documents. In this paper we focus on the second application. For better management and fruitful use of information, it is necessary to contextually segregate important/relevant information buried in a huge corpus of unstructured texts. Hence Information Extraction (IE) from unstructured texts becomes a key technology in CI that deals with different sub-topics like extraction of biomedical entity and relations, passage/paragraph level information extraction, ontological study of diseases and treatments, summarization and topic identification etc. Though literature is promising for different IE tasks for individual topics, availability of an integrated approach for contextually relevant IE from medical documents is not apparent enough. To this end, we propose a compositional approach using integration of contextually (domain specific) constructed IE modules to improve knowledge support for patient care activity. The input to this composite system is free format medical case reports containing stage wise information corresponding to the evolution path of a patient care activity. The output is a compilation of various types of extracted information organized under different tags like past medical history, sign/symptoms, test and test results, diseases, treatment and follow up. The outcome is aimed to help the health care professionals in exploring a large corpus of medical casestudies and selecting only relevant component level information according to need/interest.

This paper presents a system for automatically extracting linguistic data from digitized linguistic documents using a combination of existing software packages and custom scripts. The system is designed to leverage existing resources in online digital libraries in order to bootstrap the creation of large, multi-lingual linguistic corpora, which can then be used to conduct data-driven experimental research into cross-linguistic or universal linguistic phenomena. The system identifies instances of foreign-language text accompanied by reference-language translations within the text of printed books that have been scanned into digital format, and extracts these to produce a parallel corpus of example sentences. While the system achieves a high precision on predicting foreign text, its accuracy overall is low, and directions for improvement and future work are identified.

Due to the continuous and rampant increase in the size of domain specific data sources, there is a real and sustained need for fast processing in time-sensitive applications, such as medical record information extraction at the point of care, genetic feature extraction for personalized treatment, as well as off-line knowledge discovery such as creating evidence based medicine. Since parallel multi-string matching is at the core of most data mining tasks in these applications, faster on-line matching in static and streaming data is needed to improve the overall efficiency of such knowledge discovery. To solve this data mining need not efficiently handled by traditional information extraction and retrieval techniques, we propose a Block Suffix Shifting-based approach, which is an improvement over the state of the art multi-string matching algorithms such as Aho-Corasick, Commentz-Walter, and Wu-Manber. The strength of our approach is its ability to exploit the different block structures of domain specific data for off-line and online parallel matching. Experiments on several real world datasets show how our approach translates into significant performance improvements.

A huge number of informal messages are posted every day in social network sites, blogs and discussion forums. Emotions seem to be frequently important in these texts for expressing friendship, showing social support or as part of online arguments. Algorithms to identify sentiment and sentiment strength are needed to help understand the role of emotion in this informal communication and also to identify inappropriate or anomalous affective utterances, potentially associated with threatening behaviour to the self or others. Nevertheless, existing sentiment detection algorithms tend to be commercially-oriented, designed to identify opinions about products rather than user behaviours. This article partly fills this gap with a new algorithm, SentiStrength, to extract sentiment strength from informal English text, using new methods to exploit the de-facto grammars and spelling styles of cyberspace. Applied to MySpace comments and with a lookup table of term sentiment strengths optimised by machine learning, SentiStrength is able to predict positive emotion with 60.6% accuracy and negative emotion with 72.8% accuracy, both based upon strength scales of 1-5. The former, but not the latter, is better than baseline and a wide range of general machine learning approaches.

An overview of channel coding techniques for data hiding in still images is presented. Use of codes is helpful in reducing the bit error probability of the decoded hidden information, thus increasing the reliability of the system. First, the data hiding problem is statistically modeled for the spatial and DCT domains. Then, the bene"ts brought about by channel diversity are discussed and quanti"ed. We show that it is possible to improve on this basic scheme by employing block, convolutional and orthogonal codes, again giving analytical results. It is shown that the use of superimposed pulses does not produce any bene"t when applying them to data hiding. The possibility of using codes at the &sample level' (that is, without repeating every codeword symbol) is introduced and its potential analyzed for both hard-and soft-decision decoding. Concatenated and turbo coding are also discussed as ways of approaching the hidden channel capacity limit for the sample level case. Finally, experimental results supporting our theoretical approach are presented for some cases of interest.

A distance-based outlier detection method that finds the top outliers in an unlabeled data set and provides a subset of it, called outlier detection solving set, that can be used to predict the outlierness of new unseen objects, is proposed. The solving set includes a sufficient number of points that permits the detection of the top outliers by considering only a subset of all the pairwise distances from the data set. The properties of the solving set are investigated, and algorithms for computing it, with subquadratic time requirements, are proposed. Experiments on synthetic and real data sets to evaluate the effectiveness of the approach are presented. A scaling analysis of the solving set size is performed, and the false positive rate, that is, the fraction of new objects misclassified as outliers using the solving set instead of the overall data set, is shown to be negligible. Finally, to investigate the accuracy in separating outliers from inliers, ROC analysis of the method is accomplished. Results obtained show that using the solving set instead of the data set guarantees a comparable quality of the prediction, but at a lower computational cost.

Our KNOWITALL system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an autonomous, domain-independent, and scalable manner. In its first major run, KNOWITALL extracted over 50,000 facts with high precision, but suggested a challenge: How can we improve KNOWITALL's recall and extraction rate without sacrificing precision? This paper presents three distinct ways to address this challenge and evaluates their performance. Rule Learning learns domain-specific extraction rules. Subclass Extraction automatically identifies sub-classes in order to boost recall. List Extraction locates lists of class instances, learns a "wrapper" for each list, and extracts elements of each list. Since each method bootstraps from KNOWITALL's domain-independent methods, no hand-labeled training examples are required. Experiments show the relative coverage of each method and demonstrate their synergy. In concert, our methods gave KNOWITALL a 4-fold to 19-fold increase in recall, while maintaining high precision, and discovered 10,300 cities missing from the Tipster Gazetteer.

Because of the increasing complexity of products and the design process, as well as the popularity of computer-aided documentation tools, the number of electronic and textual design documents being generated has exploded. The availability of such extensive document resources has created new challenges and opportunities for research. These include improving design information retrieval to achieve a more coherent environment for design exploration, learning, and reuse. One critical issue is related to the construction of a structured representation for indexing design documents that record engineers' ideas and reasoning processes for a specific design. This representation should explicitly and accurately capture the important design concepts as well as the relationships between these concepts so that engineers can locate their documents of interest with less effort. For design information retrieval, we propose to use shallow natural language processing and domain-specific design ontology to automatically construct a structured and semantics-based representation from unstructured design documents. The design concepts and relationships of the representation are recognized from the document based on the identified linguistic patterns. The recognized concepts and relationships are joined to form a concept graph. The integration of these concept graphs builds an applicationspecific design ontology, which can be seen as the structured representation of the content of the corporate document repository, as well as an automatically populated knowledge base from previous designs. To improve the performance of design information retrieval, we have developed ontology-based query processing, where users' requests are interpreted based on their domain-specific meanings. Our approach contrasts with the traditionally used keyword-based search. An experiment to test the retrieval performance is conducted by using the design documents from a product design scenario. The results demonstrate that our method outperforms the keyword-based search techniques. This research contributes to the development and use of engineering ontology for design information retrieval.

A number of Learning Management Systems (LMSs) exist on the market today. A subset of a LMS is the component in which student assessment is managed. In some forms of assessment, such as open questions, the LMS is incapable of evaluating the students' responses and therefore human intervention is necessary. In order to assess at higher levels of Bloom's (1956) taxonomy, it is necessary to include open-style questions in which the student is given the task as well as the freedom to arrive at a response without the comfort of recall words and/or phrases. Automating the assessment process of open questions is an area of research that has been ongoing since the 1960s. Earlier work focused on statistical or probabilistic approaches based primarily on conceptual understanding. Recent gains in Natural Language Processing have resulted in a shift in the way in which free text can be evaluated. This has allowed for a more linguistic approach which focuses heavily on factual understanding. This study will leverage the research conducted in recent studies in the area of Natural Language Processing, Information Extraction and Information Retrieval in order to provide a fair, timely and accurate assessment of student responses to open questions based on the semantic meaning of those responses.

The paper presents some contemporary approaches to spatial environmental data analysis. The main topics are concentrated on the decision-oriented problems of environmental spatial data mining and modeling: valorization and representativity of data with the help of exploratory data analysis, spatial predictions, probabilistic and risk mapping, development and application of conditional stochastic simulation models. The innovative part of the paper presents integrated/hybrid model-machine learning (ML) residuals sequential simulations-MLRSS. The models are based on multilayer perceptron and support vector regression ML algorithms used for modeling long-range spatial trends and sequential simulations of the residuals. ML algorithms deliver non-linear solution for the spatial non-stationary problems, which are difficult for geostatistical approach. Geostatistical tools (variography) are used to characterize performance of ML algorithms, by analyzing quality and quantity of the spatially structured information extracted from data with ML algorithms. Sequential simulations provide efficient assessment of uncertainty and spatial variability. Case study from the Chernobyl fallouts illustrates the performance of the proposed model. It is shown that probability mapping, provided by the combination of ML data driven and geostatistical model based approaches, can be efficiently used in decision-making process. 

Information extraction from high spatial resolution imagery is sometimes hampered by the limited number of spectral channels available from these systems. Standard supervised classification algorithms found in commercial software packages may misclassify different features with similar spectral characteristics; leading to a high occurrence of false positives. An additional step in the information extraction process was developed incorporating the concept of object geometry. Objects are defined as a contiguous group of pixels identified as belonging to a single class in the spectral classification. Using results from the spectral classification, a supervised approach was developed using genetic programming to select and mathematically combine feature-specific shape descriptors from a larger set of shape descriptors, to form a new classifier. This investigation focused on extraction of residential housing from QuickBird and IKONOS imagery of the Mississippi Gulf Coast before and immediately after hurricane Katrina. Use of genetic programming significantly reduced false positives caused by asphalt pavement and isolated roofing material scattered throughout the image.

To map water levels related to large floods, we propose using geographical information systems to manage the vast amount of information extracted from aerial photographs. Our approach is divided into three parts: (1) segmentation of the flood plain into sectors with acceptable mean water depth, based on geographical limits and size criteria; (2) determination of minimum and maximum depths for each sector, based on the potential emergence of natural objects (vegetation, dikes, etc.); (3) improvement of water depth assessment, using all observed hydraulic connections between sectors (cracked dikes, flows, etc.). This advance is made possible by solving a constraint system linking the different estimated water levels. This method was applied to the November 1994 flood involving the Hérault River (France), using aerial photographs taken 10 h after the flood peak. Results indicate an accurate estimation of water levels, and illustrate the lateral dynamic behaviour of the flood (1 m of difference in levels between centre and edges of plain), and the impact of dikes on water levels. These results were obtained without using either general hydraulic equations or local head loss coefficients. The great quantity of fuzzy information made up for its poor quality.

Digital social platform increase the importance of image in daily life. Hence privacy of content plays an important role when content get live, so data owner put signature inform of watermark for claiming its proprietorship. This work has proposed embedding and extraction technique which increase the accuracy of watermark extraction. Proposed model utilize the frequency region of the image for embedding by swapping the LSC (Least Significant Coefficient) and MSC (Most Significant Coefficient). As per watermark information and noise level embedding of information perform swapping in LSC and MSC. After embedding each vector of DWT was used for training the Error Back Propagation Neural Network. This trained neural network extract watermark at receiver side of work. Use of neural network for watermark recovery increase watermark work performance under different attack as well. Real image dataset was used for checking the performance of proposed watermarking model. Results shows that proposed DWT Swapping and Neural Network has increase different evaluation parameter values.

Most of the existing data mining approaches to time series prediction use as training data an embed of the most recent values of the time series, following the traditional linear auto-regressive methodologies. However, in many time series prediction tasks the alternative approach that uses derivative features constructed from the raw data with the help of domain theories can produce significant prediction accuracy improvements. This is particularly noticeable when the available data includes multivariate information although the aim is still the prediction of one particular time series. This latter situation occurs frequently in financial time series prediction. This paper presents a method of feature construction based on domain knowledge that uses multivariate time series information. We show that this method improves the accuracy of next-day stock quotes prediction when compared with the traditional embed of historical values extracted from the original data.

One of the most accurate methods in Question Answering (QA) uses off-line information extraction to find answers for frequently asked questions. It requires automatic extraction from text of all relation instances for relations that users frequently ask for. In this chapter, two methods are presented for learning relation instances for relations relevant in a closed and open domain (medical) QA system. Both methods try to learn automatic dependency paths that typically connect two arguments of a given relation. The first (lightly supervised) method starts from a seed list of argument instances, and extracts dependency paths from all sentences in which a seed pair occurs. This method works well for large text collections and for seeds which are easily identified, such as named entities, and is well-suited for open domain QA. A second experiment concentrates on medical relation extraction for the question answering module of the IMIX system. The IMIX corpus is relatively small and relation instances may contain complex noun phrases that do not occur frequently in the exact same form in the corpus. In this case, learning from annotated data is necessary. Dependency patterns enriched with semantic concept labels are shown to give accurate results for relations that are relevant for a medical QA system. Both methods improve the performance of the Dutch QA system Joost.

Satire is an attractive subject in deception detection research: it is a type of deception that intentionally incorporates cues revealing its own deceptiveness. Whereas other types of fabrications aim to instill a false sense of truth in the reader, a successful satirical hoax must eventually be exposed as a jest. This paper provides a conceptual overview of satire and humor, elaborating and illustrating the unique features of satirical news, which mimics the format and style of journalistic reporting. Satirical news stories were carefully matched and examined in contrast with their legitimate news counterparts in 12 contemporary news topics in 4 domains (civics, science, business, and "soft" news). Building on previous work in satire detection, we proposed an SVMbased algorithm, enriched with 5 predictive features (Absurdity, Humor, Grammar, Negative Affect, and Punctuation) and tested their combinations on 360 news articles. Our best predicting feature combination (Absurdity, Grammar and Punctuation) detects satirical news with a 90% precision and 84% recall (F-score=87%). Our work in algorithmically identifying satirical news pieces can aid in minimizing the potential deceptive impact of satire.

Information Extraction (IE) is an important research field within the Artificial Intelligence community, for it tries to extract relevant information out of vast amounts of data. In this paper, we propose an extraction method that utilises the content and pre-defined semantics of ontologies formulated in the Web Ontology Language (OWL) to perform the extraction task. We also propose our method to detect out-of-date constructs in the ontology to suggest changes to the user. After stating the results of our evaluation, we conclude that the use of ontologies in conjunction with IESs can indeed yield feasible results and contribute to the better scalability and portability of the system.

A huge number of informal messages are posted every day in social network sites, blogs and discussion forums. Emotions seem to be frequently important in these texts for expressing friendship, showing social support or as part of online arguments. Algorithms to identify sentiment and sentiment strength are needed to help understand the role of emotion in this informal communication and also to identify inappropriate or anomalous affective utterances, potentially associated with threatening behaviour to the self or others. Nevertheless, existing sentiment detection algorithms tend to be commercially-oriented, designed to identify opinions about products rather than user behaviours. This article partly fills this gap with a new algorithm, SentiStrength, to extract sentiment strength from informal English text, using new methods to exploit the de-facto grammars and spelling styles of cyberspace. Applied to MySpace comments and with a lookup table of term sentiment strengths optimised by machine learning, SentiStrength is able to predict positive emotion with 60.6% accuracy and negative emotion with 72.8% accuracy, both based upon strength scales of 1-5. The former, but not the latter, is better than baseline and a wide range of general machine learning approaches.

The problem of constructing a tight isothetic outer (or inner) polygon covering an arbitrarily shaped 2D object on a background grid, is addressed in this paper, and a novel algorithm is proposed. Such covers have many applications to image mining, rough sets, computational geometry, and robotics. Designing efficient algorithms for these cover problems was an open problem in the literature.

Background Persistent high levels of aggressive, oppositional and impulsive behaviours, in the early lives of children, are significant risk factors for adolescent and adult antisocial behaviour and criminal activity. If the disruptive behavioural problems of young children could be prevented or significantly reduced at an early age, the trajectory of these behavioural problems leading to adolescent delinquency and adult antisocial