• Knowledge Management Research
• /
• v.23 no.2
• /
• pp.229-251
• /
• 2022

Online reviews are useful for other consumers to make reasonable purchase decisions by providing previous buyers' experiences. However, when online reviewers are biased, online reviews do not accurately reflect the true quality of the product. Therefore, we investigated the characteristics of reviewers with underreporting bias to cope with the problem of declining reliability of online reviews. In this context, this study attempted to examine the characteristics of reviewers with underreporting bias using 14,165 reviews of Steam, an online game platform. As a result of the analysis, reviewers with underreporting bias mainly write reviews positively, write reviews within a short period from the game release date, but tend to write reviews after playing games for longer time, and write reviews when purchasing high-priced games. Since this study has explored the characteristics of reviewers showing underreporting bias, it will be meaningful as a basic study to cope with the problem caused by underreporting bias.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.16-21
• /
• 2022

사전학습 말뭉치는 위키백과 문서 뿐만 아니라 인터넷 커뮤니티의 텍스트 데이터를 포함한다. 이는 언어적 관념 및 사회적 편향된 정보를 포함하므로 사전학습된 언어 모델과 파인튜닝한 언어 모델은 편향성을 내포한다. 이에 따라 언어 모델의 중립성을 평가할 수 있는 지표의 필요성이 대두되었으나, 아직까지 언어 인공지능 모델의 정치적 중립성에 대해 정량적으로 평가할 수 있는 척도는 존재하지 않는다. 본 연구에서는 언어 모델의 정치적 편향도를 정량적으로 평가할 수 있는 지표를 제시하고 한국어 언어 모델에 대해 평가를 수행한다. 실험 결과, 위키피디아로 학습된 언어 모델이 가장 정치 중립적인 경향성을 나타내었고, 뉴스 댓글과 소셜 리뷰 데이터로 학습된 언어 모델의 경우 정치 보수적, 그리고 뉴스 기사를 기반으로 학습된 언어 모델에서 정치 진보적인 경향성을 나타냈다. 또한, 본 논문에서 제안하는 평가 방법의 안정성 검증은 각 언어 모델의 정치적 편향 평가 결과가 일관됨을 입증한다.

• Management & Information Systems Review
• /
• v.34 no.3
• /
• pp.161-177
• /
• 2015

Currently, the influence of the Internet portal sites that can make it quick and easy to contact the vast amount of information is increasing. Users can connect the Internet through a portal to obtain information, such as communication between Internet users, which can be used to meet a variety of purposes. People are exposed to a variety of information from other users in the search for a movie and get information. The impact on the reviews and ratings with the limited number of characters of the film allows users to form a relationship to the movie, decide whether you want to see the movie or find another movie. but, the user can not read the whole movie review. When user see the overall evaluation, the user can receive the correct information. This research conducted a study on the prediction of the rating by the use of review data. Information of reviews, is divided into two main areas: the"fact" and "opinion". "Fact" is to convey the dispassionate information and "Opinion" is, to represent the user's feelings. In this study, we built sentiment dictionary based on the assessment and evaluation of the online review and applied to evaluate other movies. In the comparative study with a simple emotion evaluation technique, we found the suggested algorithm got the more accurate results.

• The Journal of Society for e-Business Studies
• /
• v.18 no.4
• /
• pp.315-326
• /
• 2013

Users in social media post various types of opinions such as product reviews and movie reviews. It is a common trend that customers get assistance from the opinions in making their decisions. However, as opinion usage grows, distorted feedbacks also have increased. For example, exaggerated positive opinions are posted for promoting target products. So are negative opinions which are far from common evaluations. Finding these biased opinions becomes important to keep social media reliable. Techniques of opinion mining (or sentiment analysis) have been developed to determine sentiment polarity of opinionated documents. These techniques can be utilized for finding the biased opinions. However, the previous techniques have some drawback. They categorize the text into only positive and negative, and they also need a large amount of training data to build the classifier. In this paper, we propose methods for discovering the biased opinions which are skewed from the overall common opinions. The methods are based on angle based outlier detection and personalized PageRank, which can be applied without training data. We analyze the performance of the proposed techniques by presenting experimental results on a movie review dataset.

• Journal of Service Research and Studies
• /
• v.13 no.4
• /
• pp.191-205
• /
• 2023

Artificial Intelligence (AI), especially in the domain of text-generative services, has witnessed a significant surge, with forecasts indicating the AI-as-a-Service (AIaaS) market reaching a valuation of $55.0 Billion by 2028. This research set out to explore the quality dimensions characterizing synthetic text media software, with a focus on four key players in the industry: ChatGPT, Writesonic, Jasper, and Anyword. Drawing from a comprehensive dataset of over 4,000 reviews sourced from a software evaluation platform, the study employed the Latent Dirichlet Allocation (LDA) topic modeling technique using the Gensim library. This process resulted the data into 11 distinct topics. Subsequent analysis involved comparing these topics against established AI service quality dimensions, specifically AICSQ and AISAQUAL. Notably, the reviews predominantly emphasized dimensions like availability and efficiency, while others, such as anthropomorphism, which have been underscored in prior literature, were absent. This observation is attributed to the inherent nature of the reviews of AI services examined, which lean more towards semantic understanding rather than direct user interaction. The study acknowledges inherent limitations, mainly potential biases stemming from the singular review source and the specific nature of the reviewer demographic. Possible future research includes gauging the real-world implications of these quality dimensions on user satisfaction and to discuss deeper into how individual dimensions might impact overall ratings.

• The Journal of the Korea Contents Association
• /
• v.5 no.1
• /
• pp.1-8
• /
• 2005

E-learning is the application of e-business technology and services to teaching and learning. It use of new multimedia technologies and Internet to improved the qualify of learning by facilitating access to remote resources and services. In this paper, we show a computer-based test system, which is carefully designed and implemented. The system consists of a contents delivery mechanism, computer-adaptive test algorithm, and review engine. In this papepr, we describe what are points to be considered when design and implementing a computer-based test system. In addition, this paper shows how to control the bias value for computer-adaptive algorithm using real data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.380-386
• /
• 2020

The mobile application market has grown over the past decade since the advent of smartphones, making it the largest market for electronic device software. As competition intensifies in the mobile application market, the impact of application evaluations on the consumption and usage patterns of users has also significantly increased. Therefore, research has been conducted on measures to evaluate mobile applications, but most of the research has relied on qualitative methods such as expert-centered interviews or surveys. In addition, evaluation measures are being constructed from the service provider's perspective, not from the service user's perspective. However, the possibility of application-specific analyses that minimize the subjectivity of researchers is growing, as large amounts of user review data enable quantitative analysis of actual users' assessment of applications. Therefore, this study presents a methodology that can complement current problems with existing quality assessments for mobile applications by utilizing user review data. To this end, the Topic Modeling technique LDA (Latent Dirichlet allocation) is applied in order to elucidate ways to improve existing evaluation measures from a user's perspective. The study is expected to reduce bias in service assessment due to the subjectivity of service providers and researchers as well as provide a measure of assessment by area of mobile applications from a consumer perspective.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.543-559
• /
• 2019

Data often include missing values due to various reasons. If the missing data mechanism is not MCAR, analysis based on fully observed cases may an estimation cause bias and decrease the precision of the estimate since partially observed cases are excluded. Especially when data include many variables, missing values cause more serious problems. Many imputation techniques are suggested to overcome this difficulty. However, imputation methods using parametric models may not fit well with real data which do not satisfy model assumptions. In this study, we review imputation methods using nonlinear models such as kernel, resampling, and spline methods which are robust on model assumptions. In addition, we suggest utilizing imputation classes to improve imputation accuracy or adding random errors to correctly estimate the variance of the estimates in nonlinear imputation models. Performances of imputation methods using nonlinear models are compared under various simulated data settings. Simulation results indicate that the performances of imputation methods are different as data settings change. However, imputation based on the kernel regression or the penalized spline performs better in most situations. Utilizing imputation classes or adding random errors improves the performance of imputation methods using nonlinear models.