Predicting individual retweet behavior by user similarity: A multi-task learning approach

Tang, Xing; Miao, Qiguang; Quan, Yining; Tang, Jie; Deng, Kai

doi:10.1016/j.knosys.2015.09.008

Cited by 48 publications

(30 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Much extant research uses statistical modeling to predict retweeting (e.g., Rudat, Buder, & Hesse, ; Suh, Hong, Pirolli, & Chi, ; Tang, Miao, Quan, Tang, & Deng, ; Webberley, Allen, & Whitaker, ), but these researchers provide minimal discussion of why particular tweets are retweeted and fail to consider the implications for social media practitioners. Extant research focuses on using easily appended and analyzed variables including structural elements of a tweet (e.g., the number of hashtags in the tweet) or certain tweet sender characteristics (e.g., number of sender's followers).…”

mentioning

confidence: 99%

Antecedents of Retweeting in a (Political) Marketing Context

Walker

Baines

Dimitriu

et al. 2017

Psychology and Marketing

View full text Add to dashboard Cite

Word of mouth disseminates across Twitter by means of retweeting; however, the antecedents of retweeting have not received much attention. We used the chi-square automatic interaction detection (CHAID) decision tree predictive method (Kass, 1980) with readily available Twitter data, and manually coded sentiment and content data, to identify why some tweets are more likely to be retweeted than others in a (political) marketing context. The analysis includes four CHAID models: (1) using message structure variables only, (2) source variables only, (3) message content and sentiment variables only, and (4) a combined model using source, message structure, message content, and sentiment variables. The aggregated predictive model correctly classified retweeting behavior with a 76.7% success rate. Retweeting tends to occur when the originator has a high number of Twitter followers and the sentiment of the tweet is negative, contradicting previous research (East, Hammond, & Wright, 2007 ; Wu, 2013) but concurring with others (Hennig-Thurau, Wiertz, & Feldhaus, 2014). Additionally, particular types of tweet content are associated with high levels of retweeting, in particular those tweets including fear appeals or expressing support for others, while others are associated with very low levels of retweeting, such as those mentioning the sender's personal life. Managerial implications and research directions are presented. We make a methodological contribution by illustrating how CHAID predictive modeling can be used for Twitter data analysis and a theoretical contribution by providing insights into why retweeting occurs in a (political) marketing context.

show abstract

mentioning

confidence: 99%

Antecedents of Retweeting in a (Political) Marketing Context

Walker

Baines

Dimitriu

et al. 2017

Psychology and Marketing

View full text Add to dashboard Cite

show abstract

“…Dimensión OSN e ID Número Referencias de artículos analizados Sugerencia de conductas 3 (Agrawal et al, 2011), (Aragon et al, 2013, (Chelmis et al, 2013), (Chelmis et al 2014), (Crowne et al, 2015), (Garg et al, 2011), (Heimbach & Hinz, 2016), (Jiang et al, 2014), (Korzynski, 2014), (Levy et al, 2016), (Li et al, 2016), (Liang et al, 2016), (Lim et al, 2011), (Lin et al, 2012), (Lin et al, 2014), (Lipizzi et al, 2016), (Mozafari & Hamzeh, 2015), (Palacios -Marquez et al, 2016), (Roy & Zeng, 2015), (Sankar & Ravindran, 2015), (Smith, 2013), (Subires-Mancera & Olmedo Salar, 2013), (Tang et al, 2015), (Wadhwa & Bhatia, 2015), , (Wu et al, 2015), (Zaglia et al, 2015), (Zhang, 2015), (Zhao et al, 2011), (Zinoviev, 2011).…”

Section: Análisis De Datosmentioning

confidence: 99%

La Influencia de las Redes Sociales Virtuales en la Difusión de Información y Conocimiento: Estudio de PyMES

Sánchez¹,

Schmidt²,

Zuntini³

et al. 2017

RIAE

View full text Add to dashboard Cite

El objetivo del trabajo es analizar la influencia de las redes sociales virtuales en la difusión de la información y el conocimiento. La metodología de la investigación se basa en el estudio de casos e incluy e una revisión de la literatura, la realización de cuestionarios, y el análisis de redes sociales. Como resultado del análisis de casos se observa un limitado uso de las redes sociales, a saber, LinkedIn es utilizado en forma institucional muy acotada y no contribuye a la difusión de información institucional. En el caso de aquellos que utilizan LinkedIn como herramienta para vinculaciones laborales, no evidencian que la red constituya un canal importante de transferencia y absorción de información, y no reflejan convencimiento con respecto a la contribución de las redes sociales en el éxito futuro de la organización.Palabras clave: Redes Sociales Virtuales; Difusión de Información; Difusión de Conocimiento; LinkedIn; Facebook. A INFLUÊNCIA DAS REDES SOCIAIS VIRTUAIS NA DISSEMINAÇÃO DE INFORMAÇÃO E CONHECIMENTO: ESTUDO DAS PMES RESUMOO objetivo do trabalho é analisar a influência das redes sociais virtuais na divulgação da informação e do conhecimento. A metodologia da pesquisa baseia-se em estudos de caso e inclui uma revisão da literatura, a conclusão dos questionários e a análise das redes sociais. Como resultado da análise de casos, há um uso limitado de redes sociais, ou seja, o LinkedIn é usado em uma forma institucional muito limitada e não contribui para a divulgação de informações institucionais. No caso de quem usa o LinkedIn como uma ferramenta para links de emprego, eles não mostram que a rede constitui um importante canal de transferência e absorção de informações e não reflete a convicção quanto à contribuição das redes sociais para o sucesso futuro da organização. Palavras-chave: THE INFLUENCE OF VIRTUAL SOCIAL NETWORKS IN THE DIFFUS ION OF INFORMATION AND KNOWLEDGE: SME STUDY ABSTRACTThe aim of the work is to analyze the influence of virtual social networks in the dissemination of information and knowledge. The methodology is based on case study research and includes a literature review, the use of questionnaires and social network analysis. The case studies revealed a limited use of social networks, namely LinkedIn is used in institutional form to a little extent and does not contribute to the dissemination of institutional information. In the case of those who use LinkedIn as a tool for work links, they do not evidenced that the network is an important channel of transfer and absorption of information, and it does not reflect conviction regarding the contribution of social networks in the future success of the organization.

show abstract

“…Liu and Terzi [10] approached the privacy issues raised in online social networks from the individual users viewpoint: they proposed a framework to compute the privacy score of a user. Tang et al [20] adopted a "microeconomics" approach to a model and predicted the individual retweet behavior. Xu et al [22] introduced several methods to identify online communities with similar sentiments in online social networks.…”

Section: Introductionmentioning

confidence: 99%

Estimating the similarity of social network users based on behaviors

Nguyen

Tran

Dam

et al. 2018

Vietnam J Comput Sci

View full text Add to dashboard Cite

Recently, with the express growth of social network, users have joined more and more of these networks and live their life virtually. Consequently, they create a huge data on these social networks: their profile, interest, and behavior such as post, comment, like, joining groups or communities, etc. This brings some new challenges to researchers: do users having the same profile/interest show the same behavior? And vice versa, do users having the same behavior have interest in the same things? One of the basic issues in these challenges is the problem of estimating the similarity among users on these social networks based on their profile, interest, and behavior. This paper presents a model for estimating the similarity between users based on their behavior on social networks. The considered behaviors are activities including posting entries, liking these entries, commenting and liking the comment in these entries. The model is then evaluated with a dataset-collected users from Twitter. The results show that the model estimates correctly the similarity among users in the majority of the cases.

show abstract

Predicting individual retweet behavior by user similarity: A multi-task learning approach

Cited by 48 publications

References 11 publications

Antecedents of Retweeting in a (Political) Marketing Context

Antecedents of Retweeting in a (Political) Marketing Context

La Influencia de las Redes Sociales Virtuales en la Difusión de Información y Conocimiento: Estudio de PyMES

Estimating the similarity of social network users based on behaviors

Contact Info

Product

Resources

About