scispace - formally typeset
Search or ask a question
Book ChapterDOI

Study of Socio-Linguistics Online Review System Using Sentiment Scoring Method

03 Oct 2019-pp 569-580
TL;DR: A framework is presented for mining online reviews extracted from by different reviewers & commercial websites and the potential applications of opinion mining rate the product by decision making, product analysis and improving business.
Abstract: Presently, social media are interactive and more user friendly in nature. The web users enable to provide a medium of exchange in analysing the opinionated comments of different reviewers. The review expressed in different commercial websites ranges from simple in form of sentence or paragraphs which is converted into graphical representation in form of star ratings. Commercial websites is interested to express the opinions in a broader sense driving as a revolution to e-commerce. Reviews expressed by the reviewers are also called as raters. On contrary, a huge people who are trustworthy provide fake reviews or bogus reviews to get their products. It is necessary to permit trusted people to review the products and post them on the web. Other approaches like trusted network, fixed machine address could be used for ranking the products. Since there are large number of people prefers to sell or buy products through e-commerce. The potential applications of opinion mining rate the product by decision making, product analysis and improving business. In this paper a framework is presented for mining online reviews extracted from by different reviewers & commercial websites.
Citations
More filters
Journal ArticleDOI
TL;DR: In this article , the authors extended the multi-index and multi-scale (MIMS) method into the generalized form, the online reviews are quantified by using the adverb structure scaling method, and an online reviews fusion method based on the improved TODIM (an acronym in Portuguese of interactive and multicriteria decision making) model is proposed.
Abstract: With the rapid development of computer networking technology, people pay more and more attention to the role of online reviews in management decision making. The existing methods of online reviews fusion are limited to rational decision-making behavior, which does not accord with the characteristics of evaluators’ behavior characteristics in the real environment. In order to solve the online reviews fusion problem based on bounded rational behavior which is closer to the reality of property service quality evaluation, the multi-index and multi-scale (MIMS) method is extended into the generalized form, the online reviews are quantified by using the adverb structure scaling method, and an online reviews fusion method based on the improved TODIM (an acronym in Portuguese of interactive and multi-criteria decision making) model is proposed. The feasibility and effectiveness of the proposed method are verified by an example analysis of property service quality evaluation. The research results are as follows: the adverb structure scaling method is suitable for a large number of online reviews processing, the proposed method improves the efficiency of online reviews information fusion, and it is feasible and effective to evaluate property service quality based on the bounded rationality of evaluator’s behavior.

2 citations

OtherDOI
11 Feb 2022
TL;DR: In this paper , Map Reduce structure is utilized as information text information is spoken to as slant term grid with numerical qualities and a disseminated equal preparing structure is moreover proposed for online content examination to proficiently deal with huge information.
Abstract: Large information is a term that speaks to immense volumes of fast, perplexing, and variable information that require propelled methods and advances to empower the catch, stockpiling, the board, and investigation of the information. Because of attributes like volume, veracity, and speed, large information examination is getting one of the most testing research issues. Mining significant examples from monstrous information for dynamic, forecast, and so forth is at the center of huge information examination. This field of exploration consolidates text examination and Semantic Web advances. In spite of the fact that Map Reduce can give great versatility to cluster preparing, it is not proficient to deal with unstructured information like content information. A disseminated equal preparing structure is moreover proposed for online content examination to proficiently deal with huge information. This model speaks to semantic content rundown from electronic information with the assistance of FP-tree (Frequent Pattern tree) and semantic metaphysics utilizing the space information semantic. Here, Map Reduce structure is utilized as information text information is spoken to as slant term grid with numerical qualities.

1 citations

Book ChapterDOI
01 Jan 2021
TL;DR: A novel influence maximization technique, namely the DegGreedy technique, has been illustrated along with experimental results to make a comparative analysis of the existing techniques.
Abstract: Influence maximization in online social networks (OSNs) is the problem of discovering few nodes or users in the social network termed as ‘seed nodes', which can help the spread of influence in the network. With the tremendous growth in social networking, the influence exerted by users of a social network on other online users has caught the attention of researchers to develop effective influence maximization algorithms to be applied in the field of business strategies. The main application of influence maximization is promoting the product to a set of users. However, a real challenge in influence maximization algorithms to deal with enormous amount of users or nodes obtainable in any OSN is posed. The authors focused on graph mining of OSNs for generating ‘seed sets' using standard influence maximization techniques. Many standard influence maximization models are used for calculation of spread of influence; a novel influence maximization technique, namely the DegGreedy technique, has been illustrated along with experimental results to make a comparative analysis of the existing techniques.
References
More filters
Journal ArticleDOI
TL;DR: This paper makes a comparative study of the effectiveness of ensemble technique for sentiment classification, with the aim of efficiently integrating different feature sets and classification algorithms to synthesize a more accurate classification procedure.

543 citations

Journal ArticleDOI
01 Nov 2013
TL;DR: The findings suggest that overall social media has a stronger relationship with firm stock performance than conventional media while social and conventional media have a strong interaction effect on stock performance.
Abstract: This study aims to investigate the effect of social media and conventional media, their relative importance, and their interrelatedness on short term firm stock market performances. We use a novel and large-scale dataset that features daily media content across various conventional media and social media outlets for 824 public traded firms across 6 industries. Social media outlets include blogs, forums, and Twitter. Conventional media includes major newspapers, television broadcasting companies, and business magazines. We apply the advanced sentiment analysis technique that goes beyond the number of mentions (counts) to analyze the overall sentiment of each media resource toward a specific company on the daily basis. We use stock return and risk as the indicators of companies' short-term performances. Our findings suggest that overall social media has a stronger relationship with firm stock performance than conventional media while social and conventional media have a strong interaction effect on stock performance. More interestingly, we find that the impact of different types of social media varies significantly. Different types of social media also interrelate with conventional media to influence stock movement in various directions and degrees. Our study is among the first to examine the effect of multiple sources of social media along with the effect of conventional media and to investigate their relative importance and their interrelatedness. Our findings suggest the importance for firms to differentiate and leverage the unique impact of various sources of media outlets in implementing their social media marketing strategies.

415 citations

Journal ArticleDOI
TL;DR: This thesis proposes a new senti-lexicon for the sentiment analysis of restaurant reviews using the improved Naive Bayes algorithm, and shows that when this algorithm was used and a unigrams+bigrams was used as the feature, the gap between the positive accuracy and the negative accuracy was narrowed.
Abstract: The existing senti-lexicon does not sufficiently accommodate the sentiment word that is used in the restaurant review. Therefore, this thesis proposes a new senti-lexicon for the sentiment analysis of restaurant reviews. When classifying a review document as a positive sentiment and as a negative sentiment using the supervised learning algorithm, there is a tendency for the positive classification accuracy to appear up to approximately 10% higher than the negative classification accuracy. This creates a problem of decreasing the average accuracy when the accuracies of the two classes are expressed as an average value. In order to mitigate such problem, an improved Naive Bayes algorithm is proposed. The result of the experiment showed that when this algorithm was used and a unigrams+bigrams was used as the feature, the gap between the positive accuracy and the negative accuracy was narrowed to 3.6% compared to when the original Naive Bayes was used, and that the 28.5% gap was able to be narrowed compared to when SVM was used. Additionally, the use of this algorithm based on the senti-lexicon showed an accuracy that improved by a maximum of 10.2% in recall and a maximum of 26.2% in precision compared to when SVM was used, and by a maximum of 5.6% in recall and a maximum of 1.9% in precision compared to when Naive Bayes was used.

334 citations

Journal ArticleDOI
01 Nov 2012
TL;DR: This introduction presents an overview of the current state of research in the Natural Language Processing tasks of subjectivity and sentiment analysis, as well as their application domains and closely-related research field of emotion detection.
Abstract: In this introduction, we present an overview of the current state of research in the Natural Language Processing tasks of subjectivity and sentiment analysis, as well as their application domains and closely-related research field of emotion detection. Although many definitions exist for these tasks and the research done within their frame spans over approaches with different objectives, we consider subjectivity analysis to deal with the detection of ''private states'' (opinions, emotions, sentiments, beliefs, speculations) and sentiment analysis as the task of detecting, extracting and classifying opinions and sentiments concerning different topics, as expressed in textual input. After describing the key concepts and research directions in these tasks, we present the main achievements obtained so far and the issues that remain to be tackled. Subsequently, we introduce each of the papers in this volume and present their contribution to the research areas of subjectivity and sentiment analysis. Finally, we conclude on the present state of work in these fields and reflect on the possible future developments.

230 citations

Proceedings ArticleDOI
01 Dec 2012
TL;DR: This paper discusses an approach where a publicised stream of tweets from the Twitter microblogging site are preprocessed and classified based on their emotional content as positive, negative and irrelevant; and analyses the performance of various classifying algorithmsbased on their precision and recall in such cases.
Abstract: Opinion mining and sentiment analysis is a fast growing topic with various world applications, from polls to advertisement placement. Traditionally individuals gather feedback from their friends or relatives beforepurchasing an item, but today the trend is to identify the opinions of a variety ofindividuals around the globe using microbloggingdata. This paper discusses an approach where a publicised stream of tweets from the Twitter microblogging site are preprocessed and classified based on their emotional content as positive, negative and irrelevant; and analyses the performance of various classifying algorithms based on their precision and recall in such cases. Further, the paper exemplifies the applications of this research and its limitations.

148 citations