Social Media Management in Big Data Era

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 7 of 7
  • Item
    Why Zlatan Ibrahimović is Bigger Than Manchester United: Investigating Digital Traces in Co-branding Processes on Social Media Platforms
    ( 2019-01-08) Mankevich, Vasili ; Holmström, Jonny ; McCarthy, Ian P.
    The purpose of this study is to examine the co-branding activity on social media platforms, particularly in regard to company-employee relationship. We conducted a case study of co-branding on Instagram involving the soccer club Manchester United and the soccer player Zlatan Ibrahimović. We performed sentiment and emotional tone analysis, assessed intersection of the audience and illustrated non-verbal communication used by social media users. We demonstrated how the soccer club failed to capitalize on co-branding activity as measured through consolidating the audience, generating consistent emotional response, and creating a coherent message. This paper contributes to social media management research by illustrating the difficulties associated with co-branding between personal and corporate brands as well asynchronous communication. Further, our use of digital traces and computational analysis illustrates how access to social media can illuminate research activities and provide insight about online communication.
  • Item
    How to Manage the Virtual Brand Community to Improve Brand Preference: Views from the Perceived Interactivity
    ( 2019-01-08) Zhu, Junxuan ; Zhu, Ying ; Hua, Ying
    The aim of this research is to investigate the effects of perceived interactivity of virtual brand community on customer perceived value as well as on brand preference. Data collected through a survey with 221 respondents supported the research model. This study classifies perceived interactivity as either with community or with customer, and posited that these two types have different operating mechanisms toward perceived value including emotional value, information value and social value, and brand preference. However perceived interactivity with customer does not affect brand preference significantly. Adapted by S-O-R model, perceived value mediates the relationship between the degree of interactions on sites and brand preference. These two supplements on theoretical models clearly explain the source path of brand preference.Z
  • Item
    Commercialized Content on Social Media Platforms: Exploring the Drivers of the Viewership of Paid Q&A
    ( 2019-01-08) Yang, Xueping ; Ye, Hua Jonathan
    Paying to view others’ answers is an emerging business model happening on Weibo, a Chinese version of Twitter. Yet, little is known about what drives people to pay to view others’ answers. Based on signaling theory and related literature, we develop a model to predict the viewership of paid-for answers. Using unique panel data of 417 question-to-answers, we find that answer providers’ Weibo level, the number of comments that the paid-for answer receives, as well as the question price positively affect the viewership of the paid-for answer. Our findings contribute to the literature and enlighten content providers and platform organization on how to facilitate individual users to commercialize content for profits.
  • Item
    Expanding Awareness: Comparing Location, Keyword, and Network Filtering Methods to Collect Hyperlocal Social Media Data
    ( 2019-01-08) Grace, Rob ; Halse, Shane ; Aurite, William ; Montarnal, Aurélie ; Tapia, Andrea
    Opportunities to collect real-time social media data during a crisis remain limited to location and keyword filtering despite the sparsity of geographic metadata and the tendency of keyword-based methods to capture information posted by remote rather than local users. Here we introduce a third, network filtering method that uses social network ties to infer the location of social media users in a geographic community and collect data from networks of these users during a crisis. In this paper we compare all three methods by analyzing the distribution of situational reports of infrastructure damage and service disruption across location, keyword, and network-filtered social media data during a weather emergency. We find that network filtering doubles the number of situational reports collected in real-time compared to location and keyword filtering alone, but that all three methods collect unique reports that can support situational awareness of incidents occurring across a community.
  • Item
    Opinion Formation Threshold Estimates from Different Combinations of Social Media Data-Types
    ( 2019-01-08) Asher, Derrik ; Caylor, Justine ; Doyle, Casey ; Neigel, Alexis ; Szymanski, Boleslaw ; Korniss, Gyorgy
    Passive consumption of a quantifiable amount of social media information related to a topic can cause individuals to form opinions. If a substantial amount of these individuals are motivated to take action from their recently established opinions, a movement or public opinion shift can be induced independent of the information’s veracity. Given that social media is ubiquitous in modern society, it is imperative that we understand the threshold at which social media data results in opinion formation. The present study estimates population opinion formation thresholds by querying 2222 participants about the number of various social media data-types (i.e., images, videos, and/or messages) that they would need to passively consume to form opinions. Opinion formation is assessed across three dimensions, 1) data-type(s), 2) context, 3) and source. This work provides a theoretical basis for estimating the amount of data needed to influence a population through social media information.
  • Item
    Two-Sided Value-Based Music Artist Recommendation in Streaming Music Services
    ( 2019-01-08) REN, Jing ; Kauffman, Robert ; King, Dave
    Most work on music recommendations has focused on the consumer side not the provider side. We develop a two-sided value-based approach to music artist recommendation for a streaming music scenario. It combines the value yielded for the music industry and consumers in an integrated model. For the industry, the approach aims to increase the conversion rate of potential listeners to adopters, which produces new revenue. For consumers, it aims to improve their utility related to recommendations they receive. We use one year of listening records for 15,000+ Last.fm users to train and test the proposed recommendation model on 143 artists. Compared to collaborative filtering, the results show some improvement in recommendation performance by considering both sides’ value in con-junction with other factors, including time, location, external information and listening behavior.
  • Item
    Introduction to the Minitrack on Social Media Management in Big Data Era
    ( 2019-01-08) Yan, Xiangbin ; Gan, Mingxin ; Ye, Hua Jonathan