Classifying sentiment in microblogs

Abstract

Microblogs as a new textual domain offer a unique proposition for sentiment analysis. Their short document length suggests any sentiment they contain is compact and explicit. However, this short length coupled with their noisy nature can pose difficulties for standard machine learning document representations. In this work we examine the hypothesis that it is easier to classify the sentiment in these short form documents than in longer form documents. Surprisingly, we find classifying sentiment in microblogs easier than in blogs and make a number of observations pertaining to the challenge of supervised learning for sentiment analysis in microblogs.

When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data

“…In recent times, sentiment analysis of Twitter data has received a lot of attention (Pak and Paroubek, 2010). Some of the early works by Go et al (2009) andBermingham andSmeaton (2010) use distant learning to acquire sentiment data. They show that using unigrams, bigrams and part-of-speech (POS) tags as features, SVM outperforms other classifiers like Naive Bayes and MaxEnt.…”

Lexicon Based Sentiment Analysis of Twitter Data

“…Hailong et al [18] in their study used an evaluation metrics for the comparison of existing techniques for opinion mining which includes machine learning and lexicon-based approaches. Like movie and product review, research on sentiment analysis of Twitter is also gaining ground [19], [20], [21], [22]. [23].…”

“…[23]. Lots of those studies are based on supervised learning methods like Artificial Neural Networks [24] , Distant Supervision method [19]. Most important lexicon based sentiment analysis with twitter corpus is done by Hutto and Gilbert [25].…”

“…Data was collected by the owner of dataset using Twitter API and classified based on emoticons [19]. The dataset contains 182 positive, 177 negative and 139 neutral tweets.…”

The Process of Sentiment Analysis: A Study

“…The available research shows machine learning approaches (Naive Bayes, Maximum Entropy, and SVM) to be more suitable for Twitter than the lexical-based LIWC method [4]. Similarly, classification methods (SVM, and Multinomial Naive Bayes) are more suitable than SentiWordNet for Twitter [5].…”