Twitter as a Corpus for Sentiment Analysis and Opinion Mining

By Alexander Pak, Patrick Paroubek. International Conference on Language Resources and Evaluation, 2010

2,901 citations recorded by the source corpus.

Microblogging today has become a very popular communication tool among Internet users. Millions of users share opinions on different aspects of life everyday. Therefore microblogging web-sites are rich sources of data for opinion mining and sentiment analysis. Because microblogging has appeared relatively recently, there are a few research works that were devoted to this topic. In our paper, we focus on using Twitter, the most popular microblogging platform, for the task of sentiment analysis. We show how to automatically collect a corpus for sentiment analysis and opinion mining purposes. We perform linguistic analysis of the collected corpus and explain discovered phenomena. Using the corpus, we build a sentiment classifier, that is able to determine positive, negative and neutral sentiments for a document. Experimental evaluations show that our proposed techniques are efficient and performs better than previously proposed methods. In our research, we worked with English, however, the proposed technique can be used with any other language.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/6b7fc158541d5a7be2b2465f7d8a42afa97d7ae9

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

Learning Accurate and Interpretable Classifiers Using Optimal Multi-Criteria Rules (2013, methodology): “We conducted a systematic evaluation involving benchmark data from the UCI repository [Bache and Lichman 2013], as well as real data obtained from more challenging application scenarios, such as sentiment stream analysis [Pak and Paroubek 2010; Santana et al. 2011].”
Computational approaches for mining user's opinions on the Web 2.0 (2014, background): “Other research directions focus on multilingual opinion mining (e.g. Banea, Mihalcea, & Wiebe, 2010; Steinberger, Lenkova, Kabadjov, Steinberger, & Goot van der, 2011) and on cross-domain sentiment analysis (e.g. Bollegala, Weir, & Carroll, 2011; Pan, Ni, Sun, Yang, & Chen, 2010).”
Sentiment analysis using product review data (2015, background): “Sentiment analysis [1-8], which is also known as opinion mining, studies people’s sentiments towards certain entities.”
Twitter Sentiment Analysis (2015, methodology): “Barbosa et al. reports better results for SVMs (Barbosa and Feng, 2010) while Pak et al. obtained better results for Naive Bayes (Pak and Paroubek, 2010).”
Predicting Users' Motivations behind Location Check-Ins and Utility Implications of Privacy Protection Mechanisms (2015, background): “Several other pieces of work focus on the extraction of sentiment at the post/check-in level [6], [16], [25].”
On Stopwords, Filtering and Data Sparsity for Sentiment Analysis of Twitter (2014, background): “While some works support their removal (Bakliwal et al., 2012; Pak and Paroubek, 2010; Zhang et al., 2012; Speriosu et al., 2011; Gokulakrishnan et al., 2012; Kouloumpis et al., 2011; Asiaee T et al., 2012) others claim that stopwords indeed carry sentiment information and removing them harms the pe”
The value of Twitter data for determining the emotional responses of people to urban green spaces: A case study and critical evaluation (2019, methodology): “50 The increase in social media sites such as Twitter has led to the internet becoming a place of 51 increased expression and opinion sharing on a vast range of topics (Pak and Paroubek, 2010).”
Sentiment analysis of Twitter data for predicting stock market movements (2016, background): “The information exploited from tweets are very useful for making predictions [5].”
Like It or Not (2016, methodology): “Also, a number of researchers analyzed the impact of different features on TSA and managed to establish feature selection criteria [Pak and Paroubek 2010; Agarwal et al. 2011; Kouloumpis et al. 2011].”
Sentiment Analysis on Twitter (2012, background): “As reported in one of the Indian national newspaper [3] “Union Minister for Communications and Information Minister, Kapil Sibal, proposed content screening & censorship of social networks like Twitter and Facebook”.”
Sentiment of Emojis (2015, background): “In later work, these findings were applied to automatically construct sets of positive and negative tweets [8, 18, 19], and sets of tweets with alternative sentiment categories, such as the angry and sad emotional states [11].”
Combining lexicon-based and learning-based methods for twitter sentiment analysis (2011, background): “(Park and Paroubek, 2010) built a sentiment classifier to classify tweets into positive, negative and neutral classes.”
Incorporating Structured Commonsense Knowledge in Story Completion (2018, background): “Recently, researchers studied large-scale sentiment analysis across news and blogs (Godbole, Srinivasaiah, and Skiena 2007), and also studied opinion mining on twitter (Patodkar and Sheikh 2010).”
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data (2017, background): “In recent times, sentiment analysis of Twitter data has received a lot of attention (Pak and Paroubek, 2010).”
Emotional States vs. Emotional Words in Social Media (2015, background): “This is how sentiment analysis is often used in the general area of opinion mining [27].”