NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets

TL;DR

This paper presents two advanced SVM classifiers for sentiment analysis of tweets and SMS, achieving top performance with innovative feature sets and high F-scores in both message-level and term-level tasks.

Contribution

Introduction of two state-of-the-art SVM classifiers for sentiment analysis of tweets and SMS, utilizing diverse features and achieving top results.

Findings

Message-level F-score of 69.02

Term-level F-score of 88.93

Lexicon-based features significantly improve performance

Abstract

In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a submissions stood first in both tasks on tweets, obtaining an F-score of 69.02 in the message-level task and 88.93 in the term-level task. We implemented a variety of surface-form, semantic, and sentiment features. with sentiment-word hashtags, and one from tweets with emoticons. In the message-level task, the lexicon-based features provided a gain of 5 F-score points over all others. Both of our systems can be replicated us available resources.