Pricing

login
Home / Papers / Sentiment Analysis Using Sentiment Features

Sentiment Analysis Using Sentiment Features

59 Citations2013
Seyed Ali Bahrainian, A. Dengel
2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)

A novel solution to SA of short informal texts with a main focus on Twitter posts known as "tweets" is introduced, and it is illustrated that the hybrid method outperforms the state-of-the-art unigram baseline.

Abstract

Sentiment Analysis (SA) or opinion mining has recently become the focus of many researchers, because analysis of online text is beneficial and demanded for market research, scientific surveys from psychological and sociological perspective, political polls, business intelligence, enhancement of online shopping infrastructures, etc. This paper introduces a novel solution to SA of short informal texts with a main focus on Twitter posts known as "tweets". We compare state-of-the-art SA methods against a novel hybrid method. The hybrid method utilizes a Sentiment Lexicon to generate a new set of features to train a linear Support Vector Machine (SVM) classifier. We further illustrate that our hybrid method outperforms the state-of-the-art unigram baseline.

Use the desktop version to access all features