SentiHealth: creating health-related sentiment lexicon using hybrid approach.

The exponential increase in the health-related online reviews has played a pivotal role in the development of sentiment analysis systems for extracting and analyzing user-generated health reviews about a drug or medication. The existing general purpose opinion lexicons, such as SentiWordNet has a limited coverage of health-related terms, creating problems for the development of health-based sentiment analysis applications. In this work, we present a hybrid approach to create health-related domain specific lexicon for the efficient classification and scoring of health-related users' sentiments. The proposed approach is based on the bootstrapping modal, a dataset of health reviews, and corpus-based sentiment detection and scoring. In each of the iteration, vocabulary of the lexicon is updated automatically from an initial seed cache, irrelevant words are filtered, words are declared as medical or non-medical entries, and finally sentiment class and score is assigned to each of the word. The results obtained demonstrate the efficacy of the proposed technique.

A Unified Framework for Creating Domain Dependent Polarity Lexicons from User Generated Reviews.

The exponential increase in the explosion of Web-based user generated reviews has resulted in the emergence of Opinion Mining (OM) applications for analyzing the users' opinions toward products, services, and policies. The polarity lexicons often play a pivotal role in the OM, indicating the positivity and negativity of a term along with the numeric score. However, the commonly available domain independent lexicons are not an optimal choice for all of the domains within the OM applications. The aforementioned is due to the fact that the polarity of a term changes from one domain to other and such lexicons do not contain the correct polarity of a term for every domain. In this work, we focus on the problem of adapting a domain dependent polarity lexicon from set of labeled user reviews and domain independent lexicon to propose a unified learning framework based on the information theory concepts that can assign the terms with correct polarity (+ive, -ive) scores. The benchmarking on three datasets (car, hotel, and drug reviews) shows that our approach improves the performance of the polarity classification by achieving higher accuracy. Moreover, using the derived domain dependent lexicon changed the polarity of terms, and the experimental results show that our approach is more effective than the base line methods.