The language of emotion in short blog texts

2008

Abstract Being able to automatically perceive a variety of emotions from text alone has potentially important applications in CMC and HCI that range from identifying mood from online posts to enabling dynamically adaptive interfaces. However, such ability has not been proven in human raters or computational systems. Here we examine the ability of naive raters of emotion to detect one of eight emotional categories from 50 and 200 word samples of real blog text.

Emotion Detection is one of the most emerging issues in human machine interaction. Detecting emotional state of a person from textual data is an active research field along with recognizing emotions from facial and audio information. Several methods were given to recognize emotion from text in previous years. This paper proposed a new architecture (a keyword based approach) to recognize emotions from text. In case of recognizing emotion from a piece of text document or a blog, any human can do this better than a machine only problem is he/she takes time. Proposed emotion detector system takes a text document and the emotion word ontology as inputs and produces one of the six emotion classes (i.e. love, sadness, joy, fear and surprise, anger) as the output. Every input text contains some short stories which are firstly read and assigned an emotion class manually and then that emotion class is compared to the output of the proposed system to check the accuracy of the Proposed Emotion Detector System. It is found that the Proposed Emotion Detector System produces output with the accuracy of more than 75%.

Lecture Notes in Computer Science, 2007

Finding emotions in text is an area of research with wide-ranging applications. We describe an emotion annotation task of identifying emotion category, emotion intensity and the words/phrases that indicate emotion in text. We introduce the annotation scheme and present results of an annotation agreement study on a corpus of blog posts. The average inter-annotator agreement on labeling a sentence as emotion or non-emotion was 0.76. The agreement on emotion categories was in the range 0.6 to 0.79; for emotion indicators, it was 0.66. Preliminary results of emotion classification experiments show the accuracy of 73.89%, significantly above the baseline. 1

Lecture Notes in Computer Science, 2010

Automatic data-driven analysis of mood from text is an emerging problem with many potential applications. Unlike generic text categorization, mood classification based on textual features is complicated by various factors, including its context-and user-sensitive nature. We present a comprehensive study of different feature selection schemes in machine learning for the problem of mood classification in weblogs. Notably, we introduce the novel use of a feature set based on the affective norms for English words (ANEW) lexicon studied in psychology. This feature set has the advantage of being computationally efficient while maintaining accuracy comparable to other state-of-the-art feature sets experimented with. In addition, we present results of data-driven clustering on a dataset of over 17 million blog posts with mood groundtruth. Our analysis reveals an interesting, and readily interpreted, structure to the linguistic expression of emotion, one that comprises valuable empirical evidence in support of existing psychological models of emotion, and in particular the dipoles pleasure-displeasure and activation-deactivation.

Acta Physica Polonica A, 2012

We perform a statistical analysis of emotionally annotated comments in two large online datasets, examining chains of consecutive posts in the discussions. Using comparisons with randomised data we show that there is a high level of correlation for the emotional content of messages.

PRICAI 2006: Trends in Artificial Intelligence, 2006

As an effort to detect the mood of a blog, regardless of the length and writing style, we propose a hybrid approach to detecting blog text's mood, which incorporates commonsense knowledge obtained from the general public (ConceptNet) and the Affective Norms English Words (ANEW) list. Our approach picks up blog text's unique features and compute simple statistics such as term frequency, n-gram, and point-wise mutual information (PMI) for the SVM classification method. In addition, to catch mood transitions in a given blog text, we developed a paragraph-level segmentation based on a mood flow analysis using a revised version of the GuessMood operation of ConceptNet and an ANEW-based affective sensing module. For evaluation, a mood corpus comprised of real blog texts has been built semi-automatically. Our experiments using the corpus show meaningful results for 4 mood types: happy, sad, angry, and fear.

AAAI Spring Symposium on Computational …, 2006

This short paper reports on initial experiments on the use of binary classifiers to distinguish affective states in weblog posts. Using a corpus of English weblog posts, annotated for mood by their authors, we trained support vector machine binary classifiers, ...

WASSA 2012, 2012

This paper presents our research on automatic annotation of a five-billion-word corpus of Japanese blogs with information on affect and sentiment. We first perform a study in emotion blog corpora to discover that there has been no large scale emotion corpus available for the Japanese language. We choose the largest blog corpus for the language and annotate it with the use of two systems for affect analysis: ML-Ask for word- and sentence-level affect analysis and CAO for detailed analysis of emoticons. The annotated information includes affective features like sentence subjectivity (emotive/non-emotive) or emotion classes (joy, sadness, etc.), useful in affect analysis. The annotations are also generalized on a 2-dimensional model of affect to obtain information on sentence valence/polarity (positive/negative) useful in sentiment analysis. The annotations are evaluated in several ways. Firstly, on a test set of a thousand sentences extracted randomly and evaluated by over forty respondents. Secondly, the statistics of annotations are compared to other existing emotion blog corpora. Finally, the corpus is applied in several tasks, such as generation of emotion object ontology or retrieval of emotional and moral consequences of actions.

Computer Speech & Language, 2014

This paper presents our research on automatic annotation of a five-billion-word corpus of Japanese blogs with information on affect and sentiment. We first perform a study in emotion blog corpora to discover that there has been no large scale emotion corpus available for the Japanese language. We choose the largest blog corpus for the language and annotate it with the use of two systems for affect analysis: ML-Ask for word-and sentence-level affect analysis and CAO for detailed analysis of emoticons. The annotated information includes affective features like sentence subjectivity (emotive/non-emotive) or emotion classes (joy, sadness, etc.), useful in affect analysis. The annotations are also generalized on a 2-dimensional model of affect to obtain information on sentence valence/polarity (positive/negative) useful in sentiment analysis. The annotations are evaluated in several ways. Firstly, on a test set of a thousand sentences extracted randomly and evaluated by over forty respondents. Secondly, the statistics of annotations are compared to other existing emotion blog corpora. Finally, the corpus is applied in several tasks, such as generation of emotion object ontology or retrieval of emotional and moral consequences of actions.

2009

This paper presents a method for estimating contextual appropriateness of speaker's emotions. The method is using an affect analysis system to estimate the speaker's emotions and a Web mining technique gathering from the Internet associations about emotional common-sense. The baseline of the Web mining technique, using all of the Web, is improved by restricting the query field to the contents of blogs as containing more evaluative information. A conversational agent equipped with this system could choose an appropriate conversational procedure. The proposed method is evaluated using two conversational agents. The use of blog contents improved the method in the aspect of quality as well as time of processing.