Big Data-driven Social Media Management

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 4 of 4
  • Item
    Understanding the Rise of Twitter-based cyberbullying due to COVID-19 through comprehensive statistical evaluation
    ( 2021-01-05) Karmakar, Sayar ; Das, Sanchari
    The COVID-19 pandemic has created a challenging situation for everyone, sparking digital evolution due to stay-at-home restrictions to stop the spread. This has led to an uprise of digital presence, which many hypothesize has lead to a rise of cybersecurity attacks, including cyberbullying. To evaluate the significance of COVID-19 on cyberbullying reports, we collected 454, 046 of publicly available tweets from Twitter by using MongoDB and Python libraries from January 1st, 2020–June 7th, 2020. We performed statistical analyses on the collected sample set to understand the situation from a quantitative perspective. We extracted tweets related to 27 unique keywords specific to cyberbullying, including online bullying, cyberbullying, Twitter bullying, and others. Due to the time-series’ count nature, we propose a Bayesian estimation of this count data trends utilizing an autoregressive Poisson model. A simple change-point model fails to explain the subtle changes adequately. On the other hand, our Bayesian method clearly shows the upward trend beginning in mid-March, which is reportedly the time from which the stay-at-home orders were widespread globally. The pattern remains similar if we focus on one or more such keywords instead of the total count. We also provide a fine-grained lag based analysis of our model and contrast our methods with an alternative semi-Bayesian AR-ARCH model. Overall, such analysis shows somewhat conclusive evidence of the rise around the same time as COVID.
  • Item
    Identifying Sentiment Influences Provoked by Context Factors – Results from a Data Analytics Procedure Performed on Tweets
    ( 2021-01-05) Konadl, Daniel ; Wörner, Janik ; Leist, Susanne
    Context factors have lasting impacts on people’s sentiments. Exploring impacts that different contexts have on sentiments can be crucial for managing the increasing number of communications companies nowadays maintain with customers via social media channels. To help companies prevent impacts of negative word of mouth, we provide an overview about sentiment-influential contexts for tweets as one kind of social media texts previously discussed within the literature. We collected an overall amount of 358.923.210 tweets and performed analysis to uncover the effects of continents, mobile devices’ operating systems (OS) and the combination of both on sentiments expressed within tweets. Our results show remarkable differences for tweets originating from North America and Apple devices, which turned out to be the tweets with the lowest sentiments compared to the other continents and the mobile OS Android.
  • Item
    ExeAnalyzer: A Deep Generative Adversarial Network for Multimodal Online Impression Analysis and Startup Funding Prediction
    ( 2021-01-05) Yang, Kai ; Lau, Yiu Keung Raymond
    With the rise of equity crowdfunding platforms, entrepreneurs' online impressions are of great importance to startups' initial funding success. Guided by the design science research methodology, one contribution of our research is to design a novel Generative Adversarial Network, namely ExeAnalyzer, to analyze CEOs' online impressions by using multimodal data collected from social media platforms. More specifically, ExeAnalyzer can detect CEOs' first impressions, personalities, and other sociometric attributes. Based on a dataset of 7,806 startups extracted from AngelList, another contribution of our research is the empirical analysis of the relationship between CEOs' online impressions and startups' funding successes. Our empirical analysis shows that CEOs' impression of dominance is negatively related to startups' funding performance, while the social desirability of CEOs is positively associated with startups' funding success. Our empirical study also confirms that the impression features extracted by ExeAnalyzer have significant predictive power on startups' funding performance.
  • Item
    Introduction to the Minitrack on Big Data-driven Social Media Management
    ( 2021-01-05) Yan, Xiangbin ; Gan, Mingxin ; Ye, Hua