Deakin University
Browse

Enhanced Twitter sentiment analysis by using feature selection and combination

Version 2 2024-06-06, 00:27
Version 1 2015-12-15, 11:11
conference contribution
posted on 2024-06-06, 00:27 authored by Leon YangLeon Yang, J Zhang, Lei PanLei Pan, Y Xiang
Tweet sentiment analysis is an important research topic. An accurate and timely analysis report could give good indications on the general public's opinions. After reviewing the current research, we identify the need of effective and efficient methods to conduct tweet sentiment analysis. This paper aims to achieve a high level of performance for classifying tweets with sentiment information. We propose a feasible solution which improves the level of accuracy with good time efficiency. Specifically, we develop a novel feature combination scheme which utilizes the sentiment lexicons and the extracted tweet unigrams of high information gain. We evaluate the performance of six popular machine learning classifiers among which the Naive Bayes Multinomial (NBM) classifier achieves the accuracy rate of 84.60% and takes a few minutes to complete classifying thousands of tweets.

History

Pagination

52-57

Location

Hangzhou, China

Start date

2015-11-16

End date

2015-11-18

ISBN-13

9781467384209

Language

eng

Publication classification

E Conference publication, E1 Full written paper - refereed

Copyright notice

2015, IEEE

Title of proceedings

SOCIALSEC 2015: Proceedings of the International Symposium on Security and Privacy in Social Networks and Big Data

Event

Security and Privacy in Social Networks and Big Data. International Symposium (2015 : Hangzhou, China)

Publisher

IEEE

Place of publication

Piscataway, N.J.