• Title/Summary/Keyword: Retweet

Search Result 29, Processing Time 0.033 seconds

A study on finding influential twitter users by clustering and ranking techniques (클러스터링 및 랭킹 기법을 활용한 트위터 인플루엔셜 추출 연구)

  • Choi, Jun-Il;Chang, Joong-Hyuk
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.20 no.1
    • /
    • pp.19-26
    • /
    • 2015
  • Recently, a lot of users are using social network services as the spread of SNS and generalization of smart-phone. In this study, we apply clustering and ranking method for finding twitter influential users. First, we propose five ranking elements. The five elements include the number of follow, the number of retweet, IRP, IFP and influ-score. These elements are used by centroid point of clustering methods. This study can help to find novel approaches for finding twitter influential users.

Effects of Message Polarity and Type on Word of Mouth through SNS (Social Network Service) (메시지 방향성과 유형이 SNS 구전에 미치는 영향)

  • Lee, Ju-Yang;Jang, Phil-Sik
    • Journal of Digital Convergence
    • /
    • v.11 no.6
    • /
    • pp.129-135
    • /
    • 2013
  • With the increasing use of the SNS, WOM(Word of Mouth) has become an even more powerful and useful resource for consumers and marketers. In this paper, we investigated the effects of message polarity (positive, neutral, negative) and type (factual, evaluative) on WOM through SNS (twitter). A total of 13.4 million twitter messages were collected and 1.0 million retweeted messages were analyzed. The results showed that message orientation, type, URL and hashtag have a significant (<0.01) effect on retweet counts and the interaction between message orientation and other factors were observed. It also observed that message type, URL and hashtag have significant (0.05) relationships with retweet speed.

Marketing Strategies using Social Network Analysis : Twitter's Search Network (소셜네트워크 분석을 통한 마케팅 전략 : 트위터의 검색네트워크)

  • Yoo, Byong-Kook;Kim, Soon-Hong
    • The Journal of the Korea Contents Association
    • /
    • v.13 no.5
    • /
    • pp.396-407
    • /
    • 2013
  • The role of influentials to maximize word-of-mouth effect can be seen to be very important. In this paper, we have the perspective of corporate marketing to understand Twitter influentials. We start from the point of view of who can induce eventually most exposure of tweets when he tweets the company's specific marketing messages. From this perspective, we observe both the follower influentials who have many followers and the retweet influentials who induce many retweets by visualizing graphs from network data collected via Twitter Search API. Although some users have small followers they may bring much more exposure than follower influentials if they can induce retweets by follower influentials. On the contrary, some retweet influentials who don't induce retweets by follower influentials may bring very little exposure. This suggests the fact that some small users who can induce retweets by influentials might have more important role than influentials themselves in order to increase the exposure of tweets. These users also are seen to have high centrality measures in the network structure.

A Method for Twitter Spam Detection Using N-Gram Dictionary Under Limited Labeling (트레이닝 데이터가 제한된 환경에서 N-Gram 사전을 이용한 트위터 스팸 탐지 방법)

  • Choi, Hyeok-Jun;Park, Cheong Hee
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.6 no.9
    • /
    • pp.445-456
    • /
    • 2017
  • In this paper, we propose a method to detect spam tweets containing unhealthy information by using an n-gram dictionary under limited labeling. Spam tweets that contain unhealthy information have a tendency to use similar words and sentences. Based on this characteristic, we show that spam tweets can be effectively detected by applying a Naive Bayesian classifier using n-gram dictionaries which are constructed from spam tweets and normal tweets. On the other hand, constructing an initial training set requires very high cost because a large amount of data flows in real time in a twitter. Therefore, there is a need for a spam detection method that can be applied in an environment where the initial training set is very small or non exist. To solve the problem, we propose a method to generate pseudo-labels by utilizing twitter's retweet function and use them for the configuration of the initial training set and the n-gram dictionary update. The results from various experiments using 1.3 million korean tweets collected from December 1, 2016 to December 7, 2016 prove that the proposed method has superior performance than the compared spam detection methods.

Comparative Study of Various Machine-learning Features for Tweets Sentiment Classification (트윗 감정 분류를 위한 다양한 기계학습 자질에 대한 비교 연구)

  • Hong, Cho-Hee;Kim, Hark-Soo
    • The Journal of the Korea Contents Association
    • /
    • v.12 no.12
    • /
    • pp.471-478
    • /
    • 2012
  • Various studies on sentiment classification of documents have been performed. Recently, they have been applied to twitter sentiment classification. However, they did not show good performances because they did not consider the characteristics of tweets such as tweet structure, emoticons, spelling errors, and newly-coined words. In this paper, we perform experiments on various input features (emoticon polarity, retweet polarity, author polarity, and replacement words) which affect twitter sentiment classification model based on machine-learning techniques. In the experiments with a sentiment classification model based on a support vector machine, we found that the emoticon polarity features and the author polarity features can contribute to improve the performance of a twitter sentiment classification model. Then, we found that the retweet polarity features and the replacement words features do not affect the performance of a twitter sentiment classification model contrary to our expectations.

The Role of Message Content and Source User Identity in Information Diffusion on Online Social Networks

  • Son, Insoo;Kim, Young-kyu;Lee, Dongwon
    • Asia pacific journal of information systems
    • /
    • v.25 no.2
    • /
    • pp.239-264
    • /
    • 2015
  • This study aims to investigate the effect of message content and source user identity on information diffusion in Twitter networks. For the empirical study, we collected 11,346 tweets pertaining to the three major mobile telecom carriers in Korea for three months, from September to December 2011. These tweets generated 59,111 retweets (RTs) and were retweeted at least once. Our analysis indicates that information diffusion in Twitter in terms of RT volume is affected primarily by the type of message content, such as the inclusion of corporate social responsibility activities. However, the effect of message content on information diffusion is heterogeneous to the identity of the information source. We argue that user identity affects recipients' perception of the credibility of focal information. Our study offers insights into the information diffusion mechanism in online social networks and provides managerial implications on the strategic utilization of online social networks for marketing communications with customers.

Design of Big Data Preference Analysis System (빅데이터 선호도 분석 시스템 설계)

  • Son, Sung Il;Park, Chan Khon
    • Journal of Korea Multimedia Society
    • /
    • v.17 no.11
    • /
    • pp.1286-1295
    • /
    • 2014
  • This paper suggests the way that it could improve the reliability about preference of user's feedback by adding weighting factor on sentiment analysis, and efficiently make a sentiment analysis of users' emotional perspective on the big data massively generated on twitter. To solve errors on earlier studies, this paper has improved recall and precision of sensibility determination by using sensibility dictionary subdivided sentiment polarity based on the level of sensibility and given impotance to sensibility determination by populating slang, new words, emoticons and idiomatic expressions not in the system dictionary. It has considered the context through conjunctive adverbs fixed in korean characteristics which are free to the word order. It also recognize sensibility words such as TF(Term Frequency), RT(Retweet), Follower which are weighting factors of preference and has increased reliability of preference analysis considering weight on 'a very emotional tweet', 'a recognised tweet from users' and 'a tweeter influencer'

A Reply Graph-based Social Mining Method with Topic Modeling (토픽 모델링을 이용한 댓글 그래프 기반 소셜 마이닝 기법)

  • Lee, Sang Yeon;Lee, Keon Myung
    • 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.

The Viral Effect of Online Social Network on New Products Promotion: Investigating Information Diffusion on Twitter (신제품 프로모션에 대한 온라인 소셜네트워크의 구전효과 분석 : 트위터의 정보전달과정을 중심으로)

  • Kim, Hyung-Jin;Son, In-Soo;Lee, Dong-Won
    • Journal of Intelligence and Information Systems
    • /
    • v.18 no.2
    • /
    • pp.107-130
    • /
    • 2012
  • In Twitter, a user can post a message below 140 characters on his/her account, and can also repost a message of other users who the user follows. The message posted by the user in turn can be seen and reposted by other users who follow the user, which is called Re-tweet (RT). While some messages spread widely, other messages have relatively less or no RT. What factors cause these quantity variances of RT originated from original messages? How can the messages become influential in online social networks? As an effort to answer the above questions, we focused on information vividness, message characteristics, and originator characteristics. In perspective of managerial implication, we expect that the findings of this paper will provide corporations with helpful insight on the Word-of-Mouth (WOM) effect for efficient and effective advertisements and communications when they send a message of new products or services through Social Network Services. In perspective of academic implication, we identify the effect of contents of a message on WOM, which has been dealt with by few social network researches.

A Study on the Effective Utilization of Social Media in Organizations : A Focus on Twitter (기업의 소셜미디어 활용방안에 대한 연구 : 트위터를 중심으로)

  • Lee, Jae-Nam;Byun, Eu-Jean;Han, Jae-Min
    • Journal of Information Technology Services
    • /
    • v.10 no.4
    • /
    • pp.149-169
    • /
    • 2011
  • As the number of smart phone users increases, many organizations begin to adopt social media rapidly to diversify communication channels with customers. Specifically, twitter, which supports instant and two-way communications between users and between organizations and users, has been adopted by many organizations as an efficient way not only to identify new customers but also to retain existing customers. However, little attention has been given to the issue on how organizations can effectively use twitter to improve customer satisfaction. To explore the issue, this study proposes two major dimensions, customer participation and organization resource utilization, which should be considered in building a utilization strategy for twitter in organizations. We then develop four different combinations along with these dimensions-follow, mention, retweet, and review types. Based on case studies of 27 organizations that use twitter, we evaluate the degrees of customer participation, resource utilization, and customer satisfaction, and examine matching or mismatching of the adoption purpose of twitter and its actual utilization. The study results reveal that organizations in the matching group show higher customer satisfaction that those in the mismatching group. This study sheds new light on twitter research by developing a new conceptual framework and using a case study approach to explore the relationship between the utilization strategy of twitter and customer satisfaction.