---
title: "Positive, Negative, or Neutral: Learning an Expanded Opinion Lexicon from Emoticon-Annotated Tweets"
authors:
  - "Felipe Bravo-Marquez"
  - "Eibe Frank"
  - "Bernhard Pfahringer"
doi: ""
url: "https://ijcai.org/proceedings/2015/177"
pdf: "https://ijcai.org/proceedings/2015/0177.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "1229-1234"
track: "Main Track"
keywords:
---

# Positive, Negative, or Neutral: Learning an Expanded Opinion Lexicon from Emoticon-Annotated Tweets

Felipe Bravo-Marquez, Eibe Frank, Bernhard Pfahringer

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 1229-1234.

## Abstract

We present a supervised framework for expanding an opinion lexicon for tweets. The lexicon contains part-of-speech (POS) disambiguated entries with a three-dimensional probability distribution for positive, negative, and neutral polarities. To obtain this distribution using machine learning, we propose word-level attributes based on POS tags and information calculated from streams of emoticon-annotated tweets. Our experimental results show that our method outperforms the three-dimensional word-level polarity classification performance obtained by semantic orientation, a state-of-the-art measure for establishing world-level sentiment.