Sentiment lexicon plays an important role in determining the polarity of words and proves to be an important component in sentiment analysis applications. Most of these sentiment lexicons assign a fixed polarity to each word. However, it has been noted that the polarity of words depends on how they are used and so these lexicons are unable to accurately classify the polarity of the sentiments. By considering the aspect and domain of a word will allow us to more accurately classify sentiments. This paper presents a fully automatic method to build an aspect and domain sensitive sentiment lexicon which assigns a polarity to a word depending on both the aspect and the domain. The experimental results show that our lexicon significantly outperforms other commonly used sentiment lexicons / state-of-the-art approaches. To the best of our knowledge, such a lexicon is not publicly available. As such, we also make this lexicon publicly available as we believe it will benefit the research community. In addition, we observe the long tail distribution behavior of product aspects and propose the possibility of aspect ranking by comparing the number of domains and number of sentiment words present for an aspect.
In this paper, we present a platform called Knowledge Community (K-Comm) which provides a higher level of engagement for student learning on the web. This platform is a knowledge-based social network which allows users to contribute and seek information. Users can ask questions or answer questions asked by other members. K-Comm also captures user profile, and based on a user's participation, identifies his/her area of interest and expertise. The platform is built around the philosophy that each individual is an expert in their own area and has the potential to share and contribute. K-Comm is driven by community effort and being a social network, students are more willing to participate; but unlike other social networks, K-Comm does not distract, instead, it encourages knowledge sharing and contribution.
Consumers are now relying on product reviews websites to aid them in deciding which product to buy. These sites contain large number of reviews and reading through them is tedious. In this work, we propose building a product review summarizer which will process all the reviews for a product and present them in an easy to read manner. The generated summaries show a list of product features or aspects and their corresponding rating, allowing users in comparing between different products easily. Our system first makes use of an aspect/sentiment extractor to extract the list of aspects and their sentiment words. Sentiment classification is then performed to obtain the polarity of aspects. Finally, these aspects are combined and assigned a rating to form the final summary. The experimental results on various domains have shown that our system is promising.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.