A comparative study on Twitter sentiment analysis: which features are good?
From Brede Wiki
|Conference paper (help)|
|A comparative study on Twitter sentiment analysis: which features are good?|
|Authors:||Fajri Koto, Mirna Adriani|
|Citation:||Natural Language Processing and Information Systems 9103 in Lecture Notes in Computer Science : 453-457. 2015|
|Meeting:||20th International Conference on Applications of Natural Language to Information Systems|
|Web:||DuckDuckGo Bing Google Yahoo! — Google PDF|
|Article:||Google Scholar PubMed|
|Restricted:||DTU Digital Library|
A comparative study on Twitter sentiment analysis: which features are good? is a study on Twitter sentiment analysis with multiple word lists and other features and multiple annotated Twitter corpora. The AFINN wordlist was one of the investigated word lists and it showed good performance compared to the other features, indeed the authors concluded: "By using four different datasets, the results reveal that AFINN lexicon and Senti-Strength method are the best current approaches to perform Twitter Sentiment Analysis."