• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.23-28
• /
• 2020

A comment system is essential for communication on the Internet. However, there are also malicious comments such as inappropriate expression of others by exploiting anonymity online. In order to protect users from malicious comments, classification of malicious / normal comments is necessary, and this can be implemented as text classification. Text classification is one of the important topics in natural language processing, and studies using pre-trained models such as BERT and graph structures such as GCN and GAT have been actively conducted. In this study, we implemented a comment classification system using BERT, GCN, and GAT for actual published comments and compared the performance. In this study, the system using the graph-based model showed higher performance than the BERT.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.770-773
• /
• 2019

본 논문에서는 매년 성장하는 웹툰 시장 속에서 신인 작가들이 성공할 수 있는 성공 요인을 밝히고자 하였다. 국내 1위 웹툰 플랫폼인 네이버 웹툰 중 데뷔작을 기준으로 완결 웹툰 212개, 연재 중인 웹툰 112개, 총 324개의 웹툰을 수집하여 연구를 진행하였다. 기존 선행연구와의 차별화를 두기 위해 독자의 직접적인 반응 중 하나인 댓글을 성공 요인에 포함하였다. 댓글에 담긴 긍정, 부정을 나타내는 주관을 탐지하기 위해 딥러닝을 이용하여 감성 분석을 실시하였다. 각 웹툰에 대한 댓글 반응을 포함하여 평균, '좋아요' 수, 장르 그리고 첫 화 댓글 수와 5화까지 평균 댓글 수를 흥행에 영향을 미치는 독립변수로 사용했다. 댓글 반응이 중요 요인인지를 확인하기 위해 각 모델 생성 시 댓글 반응을 포함한 모델과 포함하지 않은 모델을 생성하여 성능 평가를 실시하였다. 로지스틱 회귀분석, 아다 부스트, 그리고 서포트 벡터 머신 모델을 정확도와 ROC 그래프를 이용해 효율성을 비교하고, 이를 통해 댓글 반응을 활용한 로지스틱 회귀 모델이 가장 적합하다고 판단하였다. 모델 생성 결과 '좋아요' 수, 1화 댓글 수, 댓글 반응 순으로 성공 요인에 많은 영향을 미치는 것을 알 수 있었다.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.89-96
• /
• 2018

In online communities, a large number of participants can exchange their opinion using replies without time and space restrictions. While the online space provides quick and free communication, it also easily triggers unnecessary quarrels and conflicts. The network established on the discussion participants is an important cue to analyze the confrontation and predict serious disputes. In this paper, we present a quantitative measure for polarity observed on the discussion network built from reply exchanges in online communities. The proposed method uses the comment exchange information to establish the user interaction network graph, computes its maximum spanning tree, and then performs vertex coloring to assign two colors to each node in order to divide the discussion participants into two subsets. Using the proportion of the comment exchanges across the partitioned user subsets, we compute the polarity measure, and quantify how discussion participants are bipolarized. Using experimental results, we demonstrate the effectiveness of our method for detecting polarization and show participants of a specific discussion subject tend to be divided into two camps when they debate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.640-645
• /
• 2014

Many people use social network services as to communicate, to share an information and to build social relationships between others on the Internet. Twitter is such a representative service, where millions of tweets are posted a day and a huge amount of data collection has been being accumulated. Social mining that extracts the meaningful information from the massive data has been intensively studied. Typically, Twitter easily can deliver and retweet the contents using the following-follower relationships. Topic modeling in tweet data is a good tool for issue tracking in social media. To overcome the restrictions of short contents in tweets, we introduce a notion of reply graph which is constructed as a graph structure of which nodes correspond to users and of which edges correspond to existence of reply and retweet messages between the users. The LDA topic model, which is a typical method of topic modeling, is ineffective for short textual data. This paper introduces a topic modeling method that uses reply graph to reduce the number of short documents and to improve the quality of mining results. The proposed model uses the LDA model as the topic modeling framework for tweet issue tracking. Some experimental results of the proposed method are presented for a collection of Twitter data of 7 days.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1133-1135
• /
• 2019

기업이나 정부 등의 정책 결정에 활용하기 위해, SNS에서 사용하는 키워드를 추출하여 소비자나 유권자의 관심과 선호도를 분석하는 방법이 많이 사용되고 있다. 본 논문에서는 다수의 SNS 사이트에 올린 글과 그에 대한 공감(좋아요) 댓글, 해시태그를 분석하여 관심 키워드의 트렌드를 분석할 수 있는 시스템을 제안한다. 이 시스템에서는 각각의 SNS 글을 형태소 분석하여 키워드 빈도를 측정하고 그에 대한 공감 및 해시태그의 갯수를 계산하여 일정기간 동안의 변화를 그래프로 표시하였다. 이를 통해, 여러 사이트에서의 키워드 트렌드를 한눈에 확인할 수 있도록 했다.

• The Journal of Society for e-Business Studies
• /
• v.17 no.4
• /
• pp.69-93
• /
• 2012

Various influence-related relationships in Social Network Services (SNS) among users, posts, and user-and-post, can be expressed using links. The current research evaluates the influence of specific users or posts by analyzing the link structure of relevant social network graphs to identify influential users. We applied the concept of mutual interactions proposed for ranking semantic web resources, rather than the voting notion of Page Rank or HITS, to blogosphere, one of the early SNS. Through many experiments with network models, where the performance and validity of each alternative approach can be analyzed, we showed the applicability and strengths of our approach. The weight tuning processes for the links of these network models enabled us to control the experiment errors form the link weight differences and compare the implementation easiness of alternatives. An additional example of how to enter the content scores of commercial or spam posts into the graph-based method is suggested on a small network model as well. This research, as a starting point of the study on identifying influential users in SNS, is distinctive from the previous researches in the following points. First, various influence-related properties that are deemed important but are disregarded, such as scraping, commenting, subscribing to RSS feeds, and trusting friends, can be considered simultaneously. Second, the framework reflects the general phenomenon where objects interacting with more influential objects increase their influence. Third, regarding the extent to which a bloggers causes other bloggers to act after him or her as the most important factor of influence, we treated sequential referencing relationships with a viewpoint from that of PageRank or HITS (Hypertext Induced Topic Selection).