In this article, a method for automatic sentiment analysis of movie reviews is proposed, implemented and evaluated. In contrast to most studies that focus on determining only sentiment orientation (positive versus negative), the proposed method performs fine-grained analysis to determine both the sentiment orientation and sentiment strength of the reviewer towards various aspects of a movie. Sentences in review documents contain independent clauses that express different sentiments toward different aspects of a movie. The method adopts a linguistic approach of computing the sentiment of a clause from the prior sentiment scores assigned to individual words, taking into consideration the grammatical dependency structure of the clause. The prior sentiment scores of about 32,000 individual words are derived from SentiWordNet with the help of a subjectivity lexicon. Negation is delicately handled. The output sentiment scores can be used to identify the most positive and negative clauses or sentences with respect to particular movie aspects.
We propose a linguistic approach for sentiment analysis of message posts on discussion boards. A sentence often contains independent clauses which can represent different opinions on the multiple aspects of a target object. Therefore, the proposed system provides clause-level sentiment analysis of opinionated texts. For each sentence in a message post, it generates a dependency tree, and splits the sentence into clauses. Then it determines the contextual sentiment score for each clause utilizing grammatical dependencies of words and the prior sentiment scores of the words derived from SentiWordNet and domain specific lexicons. Negation is also delicately handled in this study, for instance, the term "not superb" is assigned a lower negative sentiment score than the term "not good". We have experimented with a dataset of movie review sentences, and the experimental results show the effectiveness of the proposed approach.
PurposeThis paper aims to investigate the characteristics and differences in sentiment expression in movie review documents from four online opinion genres – blog postings, discussion board threads, user reviews, and critic reviews.Design/methodology/approachA collection of movie review documents was harvested from the four types of web sources, and a sample of 520 movie reviews were analysed to compare the content and textual characteristics across the four genres. The analysis focused on document and sentence length, part‐of‐speech distribution, vocabulary, aspects of movies discussed, star ratings used and multimedia content in the reviews. The study also identified frequently occurring positive and negative terms in the different genres, as well as the pattern of responses in discussion threads.FindingsCritic reviews and blog postings are longer than user reviews and discussion threads, and contain longer sentences. Critic reviews and blogs contain more nouns and prepositions, whereas discussion board and user reviews have more verbs and adverbs. Critic reviews have the largest vocabulary and also the highest proportion of unique terms not found in the other genres. The most informative sentiment words in each genre are provided in the paper. With regard to content, critic reviews are more comprehensive in coverage, and discuss the movie director much more often than the other genres. User reviews discuss the scene aspects (including action and visual effects) more often than the other genres, while blogs tend to talk about the cast, and discuss the music and sound slightly more often.Research limitations/implicationsThe study only analysed movie review documents. Similar content and text analysis studies can be carried out in other domains, such as commercial product reviews, celebrity reviews, company reviews and political opinions to compare the results.Originality/valueThe main contribution of the study is the sentiment content analysis results across genres, which show the similarities and differences in content and textual characteristics in the four online opinion genres. The insights will be useful in designing automatic sentiment summarisation methods for multiple online genres.
The motivation of this study is to enhance general topical search with a sentiment-based one where the search results (snippets) returned by the web search engine are clustered by sentiment categories. Firstly we developed an automatic method to identify product review documents using the snippets (summary information that includes the URL, title, and summary text), which is genre classification. Then the identified snippets were automatically classified into positive (recommended) and negative (non-recommended) documents, which is sentiment classification. Thereafter the user may directly decide to access the positive or negative review documents. In this study we used only the snippets rather than their original full-text documents, and applied a common machine learning technique, SVM (support vector machine), and heuristic approaches to investigate how effectively the snippets can be used for genre and sentiment classification. The results show that the web search engine should improve the quality of the snippets especially for opinionated documents (i.e. review documents).
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.