Classifying sentiment in microblogs: is brevity an advantage?

By Adam Bermingham, Alan F. Smeaton. International Conference on Information and Knowledge Management, 2010

392 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ccd10aee3919a8fb1f0ea236d3d9b8557556db58

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Sentiment Analysis of Twitter Data (2011, result): “Some of the early and recent results on sentiment analysis of Twitter data are by Go et al. (2009), (Bermingham and Smeaton, 2010) and Pak and Paroubek (2010).”
Survey on mining subjective data on the web (2011, background): “Bermingham and Smeaton (2010) compared the performance of SVM and Multinomial Naive Bayes (MNB) classifiers on microblog data and reviews, and demonstrated that in most cases these classifiers yield better results on short-length, opinion-rich microblog messages.”
On Using Twitter to Monitor Political Sentiment and Predict Election Results (2011, neutral): “ods such as using sentiment lexicons (Bermingham and Smeaton, 2010).”
Exploring Demographic Language Variations to Improve Multilingual Sentiment Analysis in Social Media (2013, background): “…amount of work in subjectivity and sentiment analysis over the past decade, including, more recently, in microblogs (Barbosa and Feng, 2010; Bermingham and Smeaton, 2010; Pak and Paroubek, 2010; Bifet and Frank, 2010; Davidov et al., 2010; Li et al., 2010; Kouloumpis et al., 2011; Jiang et…”
Cyber Hate Classification: 'Othering' Language And Paragraph Embedding (2018, methodology): “n) have been used to improve the accuracy of hate speech classification [14] [?] by capturing context within a sentence that is lost in the BoW model [3,7,28,41].”
Twitter brand sentiment analysis: A hybrid system using n-gram analysis and dynamic artificial neural network (2013, methodology): “…such as the Opinion Finder lexicon (Wilson et al., 2005), with score-based methods to perform unsupervised sentiment analysis on tweets (Bermingham & Smeaton, 2010; Bollen et al., 2011; Go et al., 2009; O’Connor et al., 2010; Tumasjan et al., 2010; Bollen, Pepe, & Mao, 2011; Hu, 2013).”
Emoticon Smoothed Language Models for Twitter Sentiment Analysis (2012, methodology): “These methods are mainly fully supervised (Jansen et al. 2009; Bermingham and Smeaton 2010) which have been introduced in the Intro-duction section.”
Like It or Not (2016, background): “Bermingham and Smeaton [2010] performed a study with the aim to examine if the short length of tweets makes this task more difficult compared to longer texts. To this end, they compared Support Vector Machine (SVM) and Multinomial Naı̈ve Bayes (MNB) classifiers for blog and Twitter SA. Their results”
Approaches, Tools and Applications for Sentiment Analysis Implementation (2015, background): “For identifying the feeling polarity several key classifiers are proposed [41, 42].”