Finding Optimists and Pessimists on Twitter

Xianzhi Ruan, Steven Wilson, Rada Mihalcea

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Optimism is linked to various personal-ity factors as well as both psychologicaland physical health, but how does it re-late to the way a person tweets? We an-alyze the online activity of a set of Twit-ter users in order to determine how wellmachine learning algorithms can detect aperson’s outlook on life by reading theirtweets. A sample of tweets from each useris manually annotated in order to estab-lish ground truth labels, and classifiers aretrained to distinguish between optimisticand pessimistic users. Our results sug-gest that the words in people’s tweets pro-vide ample evidence to identify them asoptimists, pessimists, or somewhere in be-tween. Additionally, several applicationsof these trained models are explored.
Original languageEnglish
Title of host publicationThe 54th Annual Meeting of theAssociation for Computational Linguistics
Subtitle of host publicationProceedings of the Conference, Vol. 2 (Short Papers)
Place of PublicationBerlin, Germany
PublisherAssociation for Computational Linguistics
Number of pages6
ISBN (Electronic)978-1-945626-01-2
Publication statusPublished - 12 Aug 2016
Event54th Annual Meeting of the Association for Computational Linguistics - Berlin, Germany
Duration: 7 Aug 201612 Aug 2016


Conference54th Annual Meeting of the Association for Computational Linguistics
Abbreviated titleACL 2016
Internet address


Dive into the research topics of 'Finding Optimists and Pessimists on Twitter'. Together they form a unique fingerprint.

Cite this