Lexicon-based sentient analysis by mapping conveyed sentiment to intended sentiment

A. Hogenboom, M. Bal, F. Frasincar, D. Bal, U. Kaymak, F. De Jong

Research output: Contribution to journalArticleAcademicpeer-review

6 Citations (Scopus)


As consumers nowadays generate increasingly more content describing their experiences with, e.g., products and brands in various languages, information systems monitoring a universal, language-independent measure of peoples intended sentiment are crucial for todays businesses. In order to facilitate sentiment analysis of user-generated content, we propose to map sentiment conveyed by unstructured natural language text to universal star ratings, capturing intended sentiment. For these mappings, we consider a monotonically increasing step function, a naïve Bayes method, and a support vector machine. We demonstrate that the way in which natural language reveals intended sentiment differs across our datasets of Dutch and English texts. Additionally, the results of our experiments on modelling the relation between conveyed sentiment and intended sentiment suggest that language-specific sentiment scores can separate universal classes of intended sentiment from one another to a limited extent. Copyright

Original languageEnglish
Pages (from-to)125-147
Number of pages23
JournalInternational Journal of Web Engineering and Technology
Issue number2
Publication statusPublished - 1 Sep 2014


  • Naïve Bayes
  • Sentiment analysis
  • Sentiment mappings
  • Star ratings
  • Support vector machine
  • SVM
  • Web engineering

Fingerprint Dive into the research topics of 'Lexicon-based sentient analysis by mapping conveyed sentiment to intended sentiment'. Together they form a unique fingerprint.

Cite this