Subhabrata Mukherjee

Feature specific sentiment analysis for product reviews

In this paper, we present a novel approach to identify feature specific expressions of opinion in product reviews with different features and mixed emotions. The objective is realized by identifying a set of potential features in the review and extracting opinion expressions about those features by exploiting their associations. Capitalizing on the view that more closely associated words come together to express an opinion about a certain feature, dependency parsing is used to identify relations between the opinion expressions. The system learns the set of significant relations to be used by dependency parsing and a threshold parameter which allows us to merge closely associated opinion expressions. The data requirement is minimal as this is a one time learning of the domain independent parameters. The associations are represented in the form of a graph which is partitioned to finally retrieve the opinion expression describing the user specified feature. We show that the system achieves a high accuracy across all domains and performs at par with state-of-the-art systems despite its data limitations.

People on drugs: credibility of user statements in health communities

Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we propose a method for automatically establishing the credibility of user-generated medical statements and the trustworthiness of their authors by exploiting linguistic cues and distant supervision from expert sources. To this end we introduce a probabilistic graphical model that jointly learns user trustworthiness, statement credibility, and language objectivity. We apply this methodology to the task of extracting rare or unknown side-effects of medical drugs --- this being one of the problems where large scale non-expert data has the potential to complement expert medical knowledge. We show that our method can reliably extract side-effects and filter out false statements, while identifying trustworthy users that are likely to contribute valuable medical information.

TwiSent: a multistage system for analyzing sentiment in twitter

In this paper, we present TwiSent, a sentiment analysis system for Twitter. Based on the topic searched, TwiSent collects tweets pertaining to it and categorizes them into the different polarity classes positive, negative and objective. However, analyzing micro-blog posts have many inherent challenges compared to the other text genres. Through TwiSent, we address the problems of 1) Spams pertaining to sentiment analysis in Twitter, 2) Structural anomalies in the text in the form of incorrect spellings, nonstandard abbreviations, slangs etc., 3) Entity specificity in the context of the topic searched and 4) Pragmatics embedded in text. The system performance is evaluated on manually annotated gold standard data and on an automatically annotated tweet set based on hashtags. It is a common practise to show the efficacy of a supervised system on an automatically annotated dataset. However, we show that such a system achieves lesser classification accurcy when tested on generic twitter dataset. We also show that our system performs much better than an existing system.

42 - Joint Author Sentiment Topic Model

Traditional works in sentiment analysis and aspect rating prediction do not take author preferences and writing style into account during rating prediction of reviews. In this work, we introduce Joint Author Sentiment Topic Model (JAST), a generative process of writing a review by an author. Authors have different topic preferences, ‘emotional’ attachment to topics, writing style based on the distribution of semantic (topic) and syntactic (background) words and their tendency to switch topics. JAST uses Latent Dirichlet Allocation to learn the distribution of author-specific topic preferences and emotional attachment to topics. It uses a Hidden Markov Model to capture short range syntactic and long range semantic dependencies in reviews to capture coherence in author writing style. JAST jointly discovers the topics in a review, author preferences for the topics, topic ratings as well as the overall review rating from the point of view of an author. To the best of our knowledge, this is the first work in Natural Language Processing to bring all these dimensions together to have an author-specific generative model of a review.

WikiSent: weakly supervised sentiment analysis through extractive summarization with Wikipedia

This paper describes a weakly supervised system for sentiment analysis in the movie review domain. The objective is to classify a movie review into a polarity class, positive or negative, based on those sentences bearing opinion on the movie alone, leaving out other irrelevant text. Wikipedia incorporates the world knowledge of movie-specific features in the system which is used to obtain an extractive summary of the review, consisting of the reviewers opinions about the specific aspects of the movie. This filters out the concepts which are irrelevant or objective with respect to the given movie. The proposed system, WikiSent, does not require any labeled data for training. It achieves a better or comparable accuracy to the existing semi-supervised and unsupervised systems in the domain, on the same dataset. We also perform a general movie review trend analysis using WikiSent.

Where the Truth Lies: Explaining the Credibility of Emerging Claims on the Web and Social Media

The web is a huge source of valuable information. However, in recent times, there is an increasing trend towards false claims in social media, other web-sources, and even in news. Thus, factchecking websites have become increasingly popular to identify such misinformation based on manual analysis. Recent research proposed methods to assess the credibility of claims automatically. However, there are major limitations: most works assume claims to be in a structured form, and a few deal with textual claims but require that sources of evidence or counter-evidence are easily retrieved from the web. None of these works can cope with newly emerging claims, and no prior method can give user-interpretable explanations for its verdict on the claims credibility. This paper overcomes these limitations by automatically assessing the credibility of emerging claims, with sparse presence in web-sources, and generating suitable explanations from judiciously selected sources. To this end, we retrieve diverse articles about the claim, and model the mutual interaction between: the stance (i.e., support or refute) of the sources, the language style of the articles, the reliability of the sources, and the claims temporal footprint on the web. Extensive experiments demonstrate the viability of our method and its superiority over prior works. We show that our methods work well for early detection of emerging claims, as well as for claims with limited presence on the web and social media.

Credibility Assessment of Textual Claims on the Web

There is an increasing amount of false claims in news, social media, and other web sources. While prior work on truth discovery has focused on the case of checking factual statements, this paper addresses the novel task of assessing the credibility of arbitrary claims made in natural-language text - in an open-domain setting without any assumptions about the structure of the claim, or the community where it is made. Our solution is based on automatically finding sources in news and social media, and feeding these into a distantly supervised classifier for assessing the credibility of a claim (i.e., true or fake). For inference, our method leverages the joint interaction between the language of articles about the claim and the reliability of the underlying web sources. Experiments with claims from the popular website snopes.com and from reported cases of Wikipedia hoaxes demonstrate the viability of our methods and their superior accuracy over various baselines.

Incorporating author preference in sentiment rating prediction of reviews

Traditional works in sentiment analysis do not incorporate author preferences during sentiment classification of reviews. In this work, we show that the inclusion of author preferences in sentiment rating prediction of reviews improves the correlation with ground ratings, over a generic author independent rating prediction model. The overall sentiment rating prediction for a review has been shown to improve by capturing facet level rating. We show that this can be further developed by considering author preferences in predicting the facet level ratings, and hence the overall review rating. To the best of our knowledge, this is the first work to incorporate author preferences in rating prediction.

Experience-Aware Item Recommendation in Evolving Review Communities

Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a users experience level and how this is expressed in the users writing in a review community. In this paper, we model the joint evolution of user experience, interest in specific item facets, writing style, and rating behavior. This way we can generate individual recommendations that take into account the users maturity level (e.g., recommending art movies rather than blockbusters for a cinematography expert). As only item ratings and review texts are observables, we capture the users experience and interests in a latent model learned from her reviews, vocabulary and writing style. We develop a generative HMM-LDA model to trace user evolution, where the Hidden Markov Model (HMM) traces her latent experience progressing over time -- with solely user reviews and ratings as observables over time. The facets of a users interest are drawn from a Latent Dirichlet Allocation (LDA) model derived from her reviews, as a function of her (again latent) experience level. In experiments with four realworld datasets, we show that our model improves the rating prediction over state-of-the-art baselines, by a substantial margin. In addition, our model can also give some interpretations for the user experience level.Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a users experience level and how this is expressed in the users writing in a review community. In this paper, we model the joint evolution of user experience, interest in specific item facets, writing style, and rating behavior. This way we can generate individual recommendations that take into account the users maturity level (e.g., recommending art movies rather than blockbusters for a cinematography expert). As only item ratings and review texts are observables, we capture the users experience and interests in a latent model learned from her reviews, vocabulary and writing style. We develop a generative HMM-LDA model to trace user evolution, where the Hidden Markov Model (HMM) traces her latent experience progressing over time -- with solely user reviews and ratings as observables over time. The facets of a users interest are drawn from a Latent Dirichlet Allocation (LDA) model derived from her reviews, as a function of her (again latent) experience level. In experiments with five real-world datasets, we show that our model improves the rating prediction over state-of-the-art baselines, by a substantial margin. We also show, in a use-case study, that our model performs well in the assessment of user experience levels.

Credible Review Detection with Limited Information Using Consistency Features

Online reviews provide viewpoints on the strengths and shortcomings of products/services, influencing potential customers’ purchasing decisions. However, the proliferation of non-credible reviews — either fake (promoting/ demoting an item), incompetent (involving irrelevant aspects), or biased — entails the problem of identifying credible reviews. Prior works involve classifiers harnessing rich information about items/users — which might not be readily available in several domains — that provide only limited interpretability as to why a review is deemed non-credible.