Show Summary Details

Page of

PRINTED FROM OXFORD HANDBOOKS ONLINE (www.oxfordhandbooks.com). © Oxford University Press, 2018. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a title in Oxford Handbooks Online for personal use (for details see Privacy Policy and Legal Notice).

date: 15 December 2019

Abstract and Keywords

This chapter is from the forthcoming The Oxford Handbook of Affective Computing edited by Rafael Calvo, Sidney K. D'Mello, Jonathan Gratch, and Arvid Kappas. The field of affective natural language processing (NLP), in particular the recognition of emotion in text, presents many challenges. Nonetheless with current NLP techniques it is possible to approach the problem with interesting results, opening up exciting applicative perspectives for the future. In this chapter we present some explorations in dealing with the automatic recognition of affect in text. We start by describing some available lexical resources, the problem of creating a “gold standard” using emotion annotations, and the affective text task at SemEval-2007, an evaluation contest of computational semantic analysis systems. That task focused on the classification of emotions in news headlines and was meant to explore the connection between emotions and lexical semantics. Then we approach the problem of recognizing emotions in texts, presenting some state-of-the-art knowledge- and corpus-based methods. We conclude by presenting two promising lines of research in the field of affective NLP. The first approaches the related task of humor recognition; the second proposes the exploitation of extralinguistic features (e.g., music) for emotion detection.

Keywords: affective natural language processing, emotion annotation, affect in text

Access to the complete content on Oxford Handbooks Online requires a subscription or purchase. Public users are able to search the site and view the abstracts and keywords for each book and chapter without a subscription.

Please subscribe or login to access full text content.

If you have purchased a print title that contains an access token, please see the token for information about how to register your code.

For questions on access or troubleshooting, please check our FAQs, and if you can''t find the answer there, please contact us.