• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.2
• /
• pp.112-117
• /
• 2023

This study aims to find out what tourists' interests and perceptions are like through online big data. Big data for a total of five years from 2018 to 2022 were collected using the Textom program. Sentiment analysis was performed with the collected data. Sentiment analysis expresses the necessity and emotions of city tours in online reviews written by tourists using city tours. The purpose of this study is to extract and analyze keywords representing satisfaction. The sentiment analysis program provided by the big data analysis platform "TEXTOM" was used to study positives and negatives based on sentiment analysis of tourists' online reviews. Sentiment analysis was conducted by collecting reviews related to the city tour. The degree of positive and negative emotions for the city tour was investigated and what emotional words were analyzed for each item. As a result of big data sentiment analysis to examine the emotions and sentiments of tourists about the city tour, 93.8% positive and 6.2% negative, indicating that more than half of the tourists are positively aware. This paper collects tourists' opinions based on the analyzed sentiment analysis, understands the quality characteristics of city tours based on the analysis using the collected data, and sentiment analysis provides important information to the city tour platform for each region.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.652-657
• /
• 2018

With the rapid development of e-commerce, many customers can now express their opinion on various kinds of product at discussion groups, merchant sites, social networks, etc. Discerning a consensus opinion about a product sold online is difficult due to more and more reviews become available on the internet. Opinion Mining, also known as Sentiment analysis, is the task of automatically detecting and understanding the sentimental expressions about a product from customer textual reviews. Recently, researchers have proposed various approaches for evaluation in sentiment mining by applying several techniques for document, sentence and aspect level. Aspect-based sentiment analysis is getting widely interesting of researchers; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces an approach of knowledge representation for the task of analyzing product aspect rating. We focus on how to form the nature of sentiment representation from textual opinion by utilizing the representation learning methods which include word embedding and compositional vector models. Our experiment is performed on a dataset of reviews from electronic domain and the obtained result show that the proposed system achieved outstanding methods in previous studies.

• Journal of Fashion Business
• /
• v.14 no.5
• /
• pp.49-65
• /
• 2010

The purpose of this paper is to derive the categories of negative e-WOM (electronic word of mouth) via consumer review. Disclosing the details of negative e-WOM based consumer reviews has never been done before. For this reason, a content analysis was adopted to provide knowledge and understanding of the phenomenon. This paper analyzes the content of 630 consumer reviews posted on the open market internet site, www.auction.co.kr. The analysis was conducted from October 20th, 2008 to March 10th, 2009. The results indicated that the negative e-WOM based consumer reviews can be divided into two categories: the cognitive evaluation and the expression of consumer's emotion. The category of cognitive evaluation is consisted of negative e-WOM of product, negative e-WOM of service, and warning about the risk of purchasing products. The category of expressing consumers' emotion are composed of venting customers' dissatisfaction and passive response of dissatisfaction. Investigating the details of negative e-WOM has a number of implications. Most importantly, the results revealed multidimensional structure of negative e-WOM. This understanding of negative e-WOM communication allows marketers to improve products and services that better meet customers' current and future needs.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.559-568
• /
• 2014

Previous polarity classification using sentiment analysis utilizes a sentence rule by product reviews based rating points. It is difficult to be applied to blogs which have not rating of product reviews and is possible to fabricate product reviews by comment part-timers and managers who use web site so it is not easy to understand a product and store reviews which are reliability. Considering to these problems, if we analyze blogs which have personal and frank opinions and classify polarity, it is possible to understand rightly opinions for the product, store. This paper suggests that we extract high frequency vocabularies in blogs by several domains and choose topic words. Then we apply a technique of sentiment analysis and classify polarity about contents of blogs. To evaluate performances of sentiment analysis, we utilize the measurement index that use Precision, Recall, F-Score in an information retrieval field. In a result of evaluation, using suggested sentiment analysis is the better performances to classify polarity than previous techniques of using the sentence rule based product reviews.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.1-6
• /
• 2019

This study visualized users reaction about movies based on keywords with high frequency. For this work, we collected data of movie reviews on . A total of six movies were selected, and we conducted the work of data gathering and preprocessing. Semantic network analysis was used to understand the relationship among keywords. Also, NetDraw, packaged with UCINET, was used for data visualization. In this study, we identified the differences in characteristics of review contents regarding each movie. The implication of this study is that we visualized movie reviews made by sentence as keywords and explored whether it is possible to construct the interface to check users' reaction at a glance. We suggest that further studies use more diverse movie reviews, and the number of reviews for each movie is used in similar quantities for research.

• Knowledge Management Research
• /
• v.21 no.3
• /
• pp.177-195
• /
• 2020

The social consciousness on fake reviews has triggered researchers to suggest ways to cope with them by analyzing contents of fake reviews or finding ways to discover them by means of structural characteristics of them. This research tried to collect data from blog posts in Naver and detect habitual patterns users use unconsciously by variables extracted from blogs and blog posts by a machine learning model and wanted to use the technique in predicting fake reviews. Data analysis showed that there was a very high relationship between the number of all the posts registered in the blog of the writer of the related writing and the date when it was registered. And, it was found that, as model to detect advertising reviews, Random Forest is the most suitable. If a review is predicted to be an advertising one by the model suggested in this research, it is very likely that it is fake review, and that it violates the guidelines on investigation into markings and advertising regarding recommendation and guarantee in the Law of Marking and Advertising. The fact that, instead of using analysis of morphemes in contents of writings, this research adopts behavior analysis of the writer, and, based on such an approach, collects characteristic data of blogs and blog posts not by manual works, but by automated system, and discerns whether a certain writing is advertising or not is expected to have positive effects on improving efficiency and effectiveness in detecting fake reviews.

• Journal of Information Science Theory and Practice
• /
• v.3 no.1
• /
• pp.6-23
• /
• 2015

This study develops an effective method for sentiment analysis of user-generated content on drug review websites, which has not been investigated extensively compared to other general domains, such as product reviews. A clause-level sentiment analysis algorithm is developed since each sentence can contain multiple clauses discussing multiple aspects of a drug. The method adopts a pure linguistic approach of computing the sentiment orientation (positive, negative, or neutral) of a clause from the prior sentiment scores assigned to words, taking into consideration the grammatical relations and semantic annotation (such as disorder terms) of words in the clause. Experiment results with 2,700 clauses show the effectiveness of the proposed approach, and it performed significantly better than the baseline approaches using a machine learning approach. Various challenging issues were identified and discussed through error analysis. The application of the proposed sentiment analysis approach will be useful not only for patients, but also for drug makers and clinicians to obtain valuable summaries of public opinion. Since sentiment analysis is domain specific, domain knowledge in drug reviews is incorporated into the sentiment analysis algorithm to provide more accurate analysis. In particular, MetaMap is used to map various health and medical terms (such as disease and drug names) to semantic types in the Unified Medical Language System (UMLS) Semantic Network.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.457-468
• /
• 2022

With the rapid growth of the webtoon industry, a new model for webtoon applications has emerged. We have entered the era of webtoon application version 3.0 after ver 1.0 and ver 2.0. Despite these changes, research on user review analysis for webtoon applications is still insufficient. Therefore, this study aims to analyze user reviews for 'Kakao Webtoon (Daum Webtoon)' that presented the webtoon application 3.0 model. For analysis, 20,382 application reviews were collected and pre-processed, and TF-IDF, network analysis, topic modeling, and emotional analysis were conducted for each version. As a result, the user experience of the webtoon application for each version was analyzed and usability testing conducted.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.36 no.3
• /
• pp.282-296
• /
• 2012

This study identified the types of motives for reading consumer reviews of apparel products for online stores and classified shoppers into the groups based on motives. Data were collected from eleven Korean women by a focus group interview and from 313 females by an online survey. Respondents were in their 20s' and 30s' with significant experience reading consumer reviews of apparel products for online stores. The seven motives found by interviews were reduced to four types of motives by factor analysis: Right product choice and judgment of product value, risk reduction, saving time and money, and fun/killing time. The motive for the right product choice and judgment of product value was the highest and the motive for fun/killing time was the lowest. Consumers were classified into four groups based on motives: Utilitarian shoppers (25.8%), shopping-task oriented shoppers (36.8%), multiple-motive shoppers (19.7%), and moderate-motive shoppers (17.7%). There were significant differences among age groups and the amount of reading reviews posted on a product and the duration of reading reviews for online stores. In addition, managerial implications were developed.

• Asia pacific journal of information systems
• /
• v.25 no.4
• /
• pp.763-783
• /
• 2015

Online customer reviews (i.e., electronic word-of-mouth) has gained considerable interest over the past years. However, a knowledge gap exists in explaining the mechanisms among the factors that determine the product sales in online retailing environment. To fill the gap, this study adopts a principal-agent perspective to investigate the effect of customer reviews and customer incentives on product sales in online retail stores. Two customer review factors (i.e., average review ratings and the number of reviews) and two customer incentive factors (i.e., price discounts and special shipping offers) are used to predict product sales in regression analysis. The sales ranking data collected from the video game titles at Amazon.com are used to analyze the direct effects of the four factors and the interaction effects between customer review and customer incentive factors to product sales. Result reveals that most relationships exist as hypothesized. The findings support both the direct and interaction effects of customer reviews and incentive factors on product sales. Based on the findings, discussions are provided with regard to the academic and practical contributions.