This emoticon sentiment lexicon was created by:

- Alexander Hogenboom (hogenboom@ese.eur.nl, Erasmus University Rotterdam)
- Daniella Bal (daniella.bal@xs4all.nl, Erasmus University Rotterdam)
- Flavius Frasincar (frasincar@ese.eur.nl, Erasmus University Rotterdam)
- Malissa Bal (malissa.bal@xs4all.nl, Erasmus University Rotterdam)
- Franciska de Jong (f.m.g.dejong@utwente.nl, Universiteit Twente/Erasmus University Rotterdam)
- Uzay Kaymak (u.kaymak@ieee.org, Eindhoven University of Technology)

Each line in the lexicon file (EmoticonSentimentLexicon.txt) contains an emoticon and its associated sentiment according to our human annotators, separated by a tab. The sentiment of an emoticon is either -1 (negative), 0 (neutral), or 1 (positive).

A first version of this lexicon was used in the following paper:

A. Hogenboom, D. Bal, F. Frasincar, M. Bal, F. de Jong, and U. Kaymak. Exploiting Emoticons in Sentiment Analysis. In Twenty-Eighth Symposium on Applied Computing (SAC 2013), pages 703-710, Association for Computing Machinery, 2013.

The current version, in which all duplicate entries from the initial version have been removed, was used in the following article:

A. Hogenboom, D. Bal, F. Frasincar, M. Bal, F. de Jong, and U. Kaymak. Exploiting Emoticons in Polarity Classification of Text. In Journal of Web Engineering, Volume 14, Numbers 1-2, pages 22-40, Rinton Press, 2015.

This lexicon may be freely used for scientific and educational purposes, provided that a reference is made to our work in which this emoticon sentiment lexicon is introduced.