Twitter Polarity Classification with Label Propagation over Lexical Links and the Follower Graph

By Michael Speriosu, Nikita Sudan, Sid Upadhyay, Jason Baldridge. ULNLP@EMNLP, 2011

397 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e116e5f4f42cf51fb7a54a751cb19cf93eae07d5

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

Alleviating Data Sparsity for Twitter Sentiment Analysis (2012, methodology): “[18] argued that using noisy sentiment labels may hinder the performance of sentiment classifiers.”
Unsupervised sentiment analysis with emotional signals (2013, methodology): “This paper, like most previous work in sentiment analysis [10, 21, 30], focuses on the last stage of the process — polarity sentiment classification.”
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora (2016, background): “Twitter: Numerous works attempt to induce Twitter-specific sentiment lexicons using supervised approaches and features unique to that domain (e.g., follower graphs; Speriosu et al., 2011).”
Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory (2015, background): “Speriosu et al. (2011) propose a unified graph propagation model to leverage textual features (such as emoticons) as well as social information.”
A survey on classification techniques for opinion mining and sentiment analysis (2017, methodology): “Graph-based models have been used for sentiment classification (Lu 2015), automatic creating of sentiment lexicons (Hassan and Radev 2010), cross-lingual sentiment analysis (Hajmohammadi et al. 2015), and social media analysis (Speriosu et al. 2011).”
Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts (2014, methodology): “In (Speriosu et al., 2011), a label propagation (LProp) approach is proposed, while Go et al. (2009) use maximum entropy (MaxEnt), NB and SVM-based classiﬁers.”
Evaluation Datasets for Twitter Sentiment Analysis: A survey and a new dataset, the STS-Gold (2013, methodology): “Similarly [23] do not report annotation agreement among annotators.”
Exploiting social relations for sentiment analysis in microblogging (2013, methodology): “Some efforts have been made to explore the effect of external information sources [37, 41], especially social network information [35, 36], on sentiment analysis.”
A Deep Learning and Knowledge Transfer Based Architecture for Social Media User Characteristic Determination (2015, methodology): “N-gram based techniques have commonly been applied to social media analytics problems (Go et al., 2009), (Kökciyan et al., 2013), and (Speriosu et al., 2011).”
Like It or Not (2016, methodology): “The dataset has been used for both subjectivity and TSA [Saif et al. 2012b; Speriosu et al. 2011].”
Stylistic Variation in Social Media Part-of-Speech Tagging (2018, background): “Speriosu et al. (2011) constructs a heterogeneous network with tweets, users, and n-grams as nodes, and the sentiment label distributions associated with the nodes are refined by performing label propagation over social relations.”
Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets (2017, methodology): “…by an author in text, such as sentiment, emotion or affect, can give us access to a wealth of hidden information to analyze product reviews (Liu et al., 2005), political views (Speriosu et al., 2011), or to identify potentially dangerous activity on the Internet (Forsyth and Martell, 2007).”
Contextual semantics for sentiment analysis of Twitter (2016, methodology): “However, automatic labelling of training data introduces errors that may affect the performance of the classifiers (Speriosu et al., 2011).”
A Survey of Signed Network Mining in Social Media (2015, background): “2013], sentiment analysis [Speriosu et al. 2011] and feature selection [Tang and Liu 2012].”
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”
Semantic Sentiment Analysis of Twitter (2012, methodology): “[14] constructed a graph that has some of the microblogging features such as hashtags and emoticons together with users, tweets, word unigrams and bigrams as its nodes which are connected based on the link existence among them (e.”