6533b82ffe1ef96bd1296427
RESEARCH PRODUCT
A survey on emotion detection: A lexicon based backtracking approach for detecting emotion from Bengali text
Sanjida FerdousTapasy RabeyaHimel Suhita AliNarayan Ranjan Chakrabortysubject
business.industrymedia_common.quotation_subjectSupervised learning02 engineering and technologyLexiconcomputer.software_genrelanguage.human_languageEmotional competenceFocus (linguistics)SadnessBengali020204 information systems0202 electrical engineering electronic engineering information engineeringHappinesslanguage020201 artificial intelligence & image processingArtificial intelligencebusinessPsychologycomputerNatural language processingSentencemedia_commondescription
Emotion recognition ability has been introduced as a core component of emotional competence. Every emotion has different ways to be expressed such as text, speech, lyrics etc. This paper reflects the current experimental study and their outcomes on emotion detection from different textual data. In case of lexicon-based analysis, the position of emotional lexicons really varies the state of an emotion. In this empirical study, our focus was to find how people use the emotional keywords to express their emotions. We have presented an emotion detection model to extract emotion from Bengali text at the sentence level. In order to detect emotion from Bengali text, we have considered two basic emotion ‘happiness’ and ‘sadness’. Our proposed model detects emotion on the basis of the sentiment of each sentence associated with it. A lexicon based backtracking approach has been introduced for recognizing the sentiments of sentences to show how frequently people express their emotion in the last part of a sentence. Proposed method can produce a result with 77.16 accuracies.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2017-12-01 | 2017 20th International Conference of Computer and Information Technology (ICCIT) |