Semi-Supervised Polarity Lexicon Induction

By Delip Rao, Deepak Ravichandran. 2009

383 citations recorded by the source corpus.

We present an extensive study on the problem of detecting polarity of words. We consider the polarity of a word to be either positive or negative. For example, words such as good, beautiful, and wonderful are considered as positive words; whereas words such as bad, ugly, and sad are considered negative words. We treat polarity detection as a semi-supervised label propagation problem in a graph. In the graph, each node represents a word whose polarity is to be determined. Each weighted edge encodes a relation that exists between two words. Each node (word) can have two labels: positive or negative. We study this framework in two different resource availability scenarios using WordNet and OpenOffice thesaurus when WordNet is not available. We report our results on three different languages: English, French, and Hindi. Our results indicate that label propagation improves significantly over the baseline and other semi-supervised learning methods like Mincuts and Randomized Mincuts for this task.

Subfields: Artificial Intelligence

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

Attention-based LSTM for Aspect-level Sentiment Classification (2016, background): “With the abundance of sentiment lexicons (Rao and Ravichandran, 2009; Perez-Rosas et al., 2012; Kaji and Kitsuregawa, 2007), the lexicon-based features were built for sentiment analysis (Mohammad et al.”
Learning Attitudes and Attributes from Multi-aspect Reviews (2012, background): “Our work is also related to the discovery of sentiment lexicons [28], [34].”
Learning Sentiment Lexicons in Spanish (2012, methodology): “The work closest to ours is authored by (Rao and Ravichandran, 2009), who introduce a lexicon induction method that uses the WordNet graph and the relationships it entails to extend polarity classification to other words using graph based semisupervised learning algorithms, such as mincuts, randomiz”
Sentiment Classification of Reviews Using SentiWordNet (2009, background): “As noted in [15], term relationships in the WordNet database fo rm a highly disconnected graph, and thus expansion of opinion information from a core o f seed words by examining semantic relationships such as synonyms and antonyms is bound to be restri ct d only to a subset of terms.”
Attentional Encoder Network for Targeted Sentiment Classification (2019, methodology): “…machine learning methods, including rule-based methods (Ding et al., 2008) and statistic-based methods (Jiang et al., 2011), mainly focus on extracting a set of features like sentiment lexicons features and bag-of-words features to train a sentiment classifier (Rao and Ravichandran, 2009).”
SenticNet 3: A Common and Common-Sense Knowledge Base for Cognition-Driven Sentiment Analysis (2014, methodology): “…1992; Wiebe, Wilson, and Cardie 2005); lexical affinity, which assigns arbitrary words a probabilistic affinity for a particular topic or emotion (Rao and Ravichandran 2009; Weichselbraun , Gindl, and Scharl 2013); statistical methods, which calculate the valence of word co-occurrence…”
Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach (2014, methodology): “Then, graph propagation algorithms, such as pagerank (Esuli and Sebastiani, 2007), label propagation (Rao and Ravichandran, 2009) or random walk (Baccianella et al., 2010), are utilized to iteratively calculate the sentiment score of each item.”
A survey on sentiment analysis methods, applications, and challenges (2022, background): “In work of Bordes et al. (2014), Bhaskar et al. (2015), Rao and Ravichandran (2009) worked on the WordNet dataset in their work.”
A review of natural language processing techniques for opinion mining systems (2017, methodology): “Some methods have been proposed to create lexicons from some seed words through synonyms and antonyms [31, 32, 33].”
Twitter Polarity Classification with Label Propagation over Lexical Links and the Follower Graph (2011, positive): “Several have used label propagation starting with a small number of hand-labeled words to induce a lexicon for use in polarity classiﬁcation (Blair-Goldensohn et al., 2008; Rao and Ravichandran, 2009; Brody and El-hadad, 2010).”
Compositional Matrix-Space Models for Sentiment Analysis (2011, background): “There has been a lot of research in determining the sentiment of words and constructing polarity dictionaries (Hatzivassiloglou and McKeown, 1997; Wiebe, 2000; Rao and Ravichandran, 2009; Mohammad et al., 2009; Velikovich et al., 2010).”
Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora (2016, background): “Resource-light: Accurate performance without massive corpora or hand-curated resources.”
Exploring Demographic Language Variations to Improve Multilingual Sentiment Analysis in Social Media (2013, methodology): “For example, Rao and Ravichandran (2009) construct HINDI and FRENCH sentiment lexicons using relations in WordNet (Miller, 1995), Rosas et. al.”
Aspect and sentiment unification model for online review analysis (2011, methodology): “, SentiWordNet) can be used or a new set of words may be obtained by using sentiment propagation techniques [14, 17, 20].”
Lexicon-Based Methods for Sentiment Analysis (2011, background): “We conclude the section with tests that show SO-CAL’s performance on different data sets.”