Alleviating Data Sparsity for Twitter Sentiment Analysis

By Hassan Saif, Yulan He, Harith Alani. 2012

227 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019, background): “This can be exacerbated by platform functionality design (e.g., limiting the length of users’ posts) (Saif et al., 2012), and may aﬀect, for instance, data retrieval tasks (Naveed et al., 2011).”
Ontology-based sentiment analysis of twitter posts (2013, background): “As outlined in (Saif et al., 2012), in relation to sentiment analysis which is derived from Twitter posts, the following approaches can be distinguished:”
On Stopwords, Filtering and Data Sparsity for Sentiment Analysis of Twitter (2014, background): “This phenomena increases the level of data sparsity, affecting the performance of Twitter sentiment classifiers (Saif et al., 2012a).”
Evaluation Datasets for Twitter Sentiment Analysis: A survey and a new dataset, the STS-Gold (2013, methodology): “It is worth noting that the annotation was done using Tweenator,(8) an online tool that we previously built to annotate tweet messages [20].”
Twitter brand sentiment analysis: A hybrid system using n-gram analysis and dynamic artificial neural network (2013, methodology): “Researchers have utilized semantic measures in the tweet feature representations by incorporating sentiment lexicon terms (Agarwal, Xie, Vovsha, Rambow, & Passonneau, 2011; Barbosa & Feng, 2010; Jiang, Yu, Zhou, Liu, & Zhao, 2011; Kouloumpis, Wilson, & Moore, 2011; Saif, He, & Alani, 2012).”
Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory (2015, background): “Saif et al. (2012a; 2012b) make use of sentiment-topic features and entities extracted by a third-party service to ease data sparsity.”
Like It or Not (2016, methodology): “One interesting study focused on reducing data sparseness of tweets was presented by Saif et al. [2012a], who proposed semantic smoothing to reduce the sparseness.”