Browsing by Author "Song, Ziqian"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Collaborative Filtering for IDEAL
    Li, Tianyi; Nakate, Pranav; Song, Ziqian (2016-05-04)
    The students of CS5604 (Information Retrieval and Storage), have been building an Information Retrieval System based on tweet and webpage collections of the Digital Library Research Laboratory (DLRL). The students have been grouped into smaller teams such as Front End team, Solr team, and Collaborative Filtering team, which are building the individual subsystems of the entire project. The teams are collaborating among themselves to integrate their individual subsystems. The Collaborative Filtering (CF) team has been building a recommendation system that can recommend tweets and webpages to users based on content similarity of document pairs as well as user pair similarity. We have finished building the recommendation system so that when the user starts using the system they will be recommended to documents that are similar to those returned by their queries. As more users coming in, they will be also referred to documents that similar users were interested in.
  • Thumbnail Image
    A Hybrid Model for Role-related User Classification on Twitter
    Li, Liuqing; Song, Ziqian; Zhang, Xuan; Fox, Edward A. (Virginia Tech, 2018-11-15)
    To aid a variety of research studies, we propose TWIROLE, a hybrid model for role-related user classification on Twitter, which detects male-related, female-related, and brand-related (i.e., organization or institution) users. TWIROLE leverages features from tweet contents, user profiles, and profile images, and then applies our hybrid model to identify a user’s role. To evaluate it, we used two existing large datasets about Twitter users, and conducted both intra- and inter-comparison experiments. TWIROLE outperforms existing methods and obtains more balanced results over the several roles. We also confirm that user names and profile images are good indicators for this task. Our research extends prior work that does not consider brand-related users, and is an aid to future evaluation efforts relative to investigations that rely upon self-labeled datasets.
  • Thumbnail Image
    The Impact of Corporate Crisis on Stock Returns: An Event-driven Approach
    Song, Ziqian (Virginia Tech, 2020-08-25)
    Corporate crisis events such as cyber attacks, executive scandals, facility accidents, fraud, and product recalls can damage customer trust and firm reputation severely, which may lead to tremendous loss in sales and firm equity value. My research aims to integrate information available on the market to assist firms in tackling crisis events, and to provide insight for better decision making. We first study the impact of crisis events on firm performance. We build a hybrid deep learning model that utilizes information from financial news, social media, and historical stock prices to predict firm stock performance during firm crisis events. We develop new methodologies that can extract, select, and represent useful features from textual data. Our hybrid deep learning model achieves 68.8% prediction accuracy for firm stock movements. Furthermore, we explore the underlying mechanisms behind how stakeholders adopt and propagate event information on social media, as well as how this would impact firm stock movements during such events. We adopt an extended epidemiology model, SEIZ, to simulate the information propagation on social media during a crisis. The SEIZ model classifies people into four states (susceptible, exposed, infected, and skeptical). By modeling the propagation of firm-initiated information and user-initiated information on Twitter, we simulate the dynamic process of Twitter stakeholders transforming from one state to another. Based on the modeling results, we quantitatively measure how stakeholders adopt firm crisis information on Twitter over time. We then empirically evaluate the impact of different information adoption processes on firm stock performance. We observe that investors often react very positively when a higher portion of stakeholders adopt the firm-initiated information on Twitter, and negatively when a higher portion of stakeholders adopt user-initiated information. Additionally, we try to identify features that can indicate the firm stock movement during corporate events. We adopt Layer-wised Relevance Propagation (LRP) to extract language features that can be the predictive variables for stock surge and stock plunge. Based on our trained hybrid deep learning model, we generate relevance scores for language features in news titles and tweets, which can indicate the amount of contributions these features made to the final predictions of stock surge and plunge.