Effectiveness gain of polarity detection through topic domains (original) (raw)
Related papers
Polarity Detection at Sentence Level
International Journal of Computer Applications, 2014
Opinions bear a very important place in the life of human beings. Human Beings are always surrounded by opinions, when a decision has to be taken; people always want to know the opinions of others. But as the impact of the web is increasing day by day, Web documents can be seen as a new source of opinions for the people. Large numbers of reviews are available on the Web related to every product. Whenever a customer buys any product, they express their feedbacks as opinions on the e-commerce website, thus it is very important to automatically analyze the huge amount of information on the web and develop methods to automatically classify the reviews. Opinion Mining or Sentiment Analysis is the mining of attitudes, opinions, and emotions automatically from text, speech, and database sources through Natural Language Processing (NLP). In this paper an opinion mining system is proposed using unsupervised technique to determine the polarity of sentences i.e. to classify the sentences as positive, negative or neutral. Negation is also handled in the proposed system. Experimental results using reviews of products show the effectiveness of the system.
Automatic Construction of Domain-Specific Sentiment Lexicons for Polarity Classification
Advances in Intelligent Systems and Computing, 2017
The article describes a strategy to build sentiment lexicons (positive and negative words) from corpora. Special attention will paid to the construction of a domain-specific lexicon from a corpus of movie reviews. Polarity words of the lexicon are assigned weights standing for different degrees of positiveness and negativeness. This lexicon is integrated into a sentiment analysis system in order to evaluate its performance in the task of sentiment classification. The experiments performed shows that the lexicon we generated automatically outperforms other manual lexicons when they are used as features of a supervised sentiment classifier.
Detecting sentence level polarity
Sentiment Analysis is a discipline that aims at identifying and extract the subjectivity expressed by authors of information sources. Sentiment Analysis can be applied at different level of granularity and each of them still has open issues. In this paper we propose a completely unsupervised approach aimed at inducing a set of words patterns that change the polarity of subjective terms. This is a very important task because, while sentiment lexicons are valid tools that can be used to identify the polarity at word level, working at different level of granularity they are no longer sufficient, because of the various aspects to consider like the context, the use of negations and so on that can change the polarity of subjective terms.
Building Phrase Polarity Lexicons for Sentiment Analysis
International Journal of Interactive Multimedia and Artificial Intelligence
Many approaches to sentiment analysis benefit from polarity lexicons. Most polarity lexicons include a list of polar (positive/negative) words, and sentiment analysis systems attempt to capture the occurrence of those words in text using polarity lexicons. Although there exist some polarity lexicons in many natural languages, most languages suffer from the lack of phrase polarity lexicons. Phrases play an important role in sentiment analysis because the polarity of a phrase cannot always be estimated based on the polarity of its parts. In this work, a hybrid approach is proposed for building phrase polarity lexicons which is experimented on Turkish as a low-resource language. The obtained classification accuracies in extracting and classifying phrases as positive, negative, or neutral, approve the effectiveness of the proposed methodology.
Computing Sentiment Polarity of Texts at Document and Aspect Levels
ECTI Transactions on Computer and Information Technology (ECTI-CIT), 1970
This paper presents our experimental work on two aspects of sentiment analysis. First, we evaluate the performance of different machine learning as well as lexicon based methods for sentiment analysis of texts obtained from variety of sources. Our performance evaluation results are on six different datasets of different kinds, including movie reviews, blog posts and twitter feeds. To the best of our knowledge no such work on comprehensive evaluative account involving different techniques on variety of datasets have been reported earlier. The second major work that we report here is about the heuristic based scheme that we devised for aspect-level sentiment profile generation of movies. Our algorithmic formulation parses the user reviews for a movie and generates a sentiment polarity profile of the movie based on opinion expressed on various aspects in the user reviews. The results obtained for the aspect-level computation are also compared with the corresponding results obtained fro...
Information Processing & Management, 2021
Lexicon based methods use Sentiment Orientation (SO) scores of words contained in the text for polarity determination of documents. These SO scores are obtained from sentiment lexicons like MPQA and SentiWordNet which are built using methods such as Pointwise Mutual Information (PMI) to calculate the SO scores of the words.. The more popular PMI based methods for creating lexicons do not make use of the rich information that can be obtained from star ratings available for text documents such as reviews available for various product categories on online platforms like amazon, yelp.com or IMDB. Star ratings have only recently been used in some studies to calculate SO value of words in reviews for developing domain specific sentiment lexicons. This paper also makes use of star ratings but proposes a novel approach 'SentiDraw' where the probability distribution of words across reviews with different star ratings is used to calculate their SO scores. A comprehensive assessment of SentiDraw performance across multiple domains and datasets is also presented by comparing it with other methods that make use of star ratings of reviews for building lexicons. The results show that lexicons built with SentiDraw method delivers superior performance versus other lexicons in six out of nine cases. The accuracy score of sentiment classification using SentiDraw method ranges from 78.0% to 81.6% across domains and SentiDraw lexicon built using Hollywood dataset outperforms any other purely lexicon based method known to authors on the most experimented datasets like Cornell Movie Reviews Dataset (CMRD) and Large Movie Review Dataset (LMRD). Finally, a hybrid approach is also proposed that uses SentiDraw along with supervised methods to deliver state-of-art performance for polarity determination of reviews.
A semantic approach for topic-based polarity detection: a case study in the Spanish language
Procedia Computer Science, 2019
In recent years, surprising amounts of news, messages, and reviews of products and services are generated in the online social media. Several efforts are being dedicated to detecting topics, as well as mining opinions in these unstructured texts. There are several approaches that compute opinion polarity, and some of them consider topics for their textual analysis. Nevertheless, discovering topics in opinions continues being challenging; due to opinions are generally short and informally written. Besides, opinions do not have a defined structure in several paragraphs; they are presented most of the time as a composition in a paragraph. In this paper, we propose a method to detect polarity in opinions by topics. Our proposal contributes to the fuzzy polarity calculation of detected topics in Spanish opinions. This method is comprised of three main steps: (1) preprocessing, (2) topic detection and (3) fuzzy polarity detection. It is important to notice the added values of this paper are: (1) the topic detection proposal based on the semantic processing when applying the clustering algorithm on opinion sentences, and (2) the evaluation of different aggregation operators for determining the opinion polarity from a fuzzy logic perspective. Aiming at assessing the quality of the resultant polarity detection by topics, we have conducted two main experiments over the Spanish corpus of opinions about Andalusian Hotels from the TripAdvisor site. The results have shown that our method is able to detect the topics correctly, as well as calculating their opinion polarities.
Using Syntactic and Contextual Information for Sentiment Polarity Analysis
ICCIT 2009, 2009
A new method for sentiment polarity analysis is presented. The method first assigns scores to a sentence using SentiWordNet and then uses heuristics to handle context dependent sentiment expressions. Instead of using score of all synsets of a word listed in SentiWordNet we use score of synsets of the same parts of speech only. Our method shows significant improvement on movie-review dataset over the baseline.
A Comparison of Domain-based Word Polarity Estimation using different Word Embeddings
2016
A key point in Sentiment Analysis is to determine the polarity of the sentiment implied by a certain word or expression. In basic Sentiment Analysis systems this sentiment polarity of the words is accounted and weighted in different ways to provide a degree of positivity/negativity. Currently words are also modelled as continuous dense vectors, known as word embeddings, which seem to encode interesting semantic knowledge. With regard to Sentiment Analysis, word embeddings are used as features to more complex supervised classification systems to obtain sentiment classifiers. In this paper we compare a set of existing sentiment lexicons and sentiment lexicon generation techniques. We also show a simple but effective technique to calculate a word polarity value for each word in a domain using existing continuous word embeddings generation methods. Further, we also show that word embeddings calculated on in-domain corpus capture the polarity better than the ones calculated on general-do...
A Unified Framework for Creating Domain Dependent Polarity Lexicons from User Generated Reviews
The exponential increase in the 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.