VTechWorks staff will be away for the Thanksgiving holiday beginning at noon on Wednesday, November 27, through Friday, November 29. We will resume normal operations on Monday, December 2. Thank you for your patience.

Browsing by Author "Mitra, Tanushree"

Now showing 1 - 17 of 17
  • Thumbnail Image
    ALJI: Active Listening Journal Interaction
    Sullivan, Patrick Ryan (Virginia Tech, 2019-10-29)
    Depression is a crippling burden on a great many people, and it is often well hidden. Mental health professionals are able to treat depression, but the general public is not well versed in recognizing depression symptoms or assessing their own mental health. Active Listening Journal Interaction (ALJI) is a computer program that seeks to identify and refer people suffering with depression to mental health support services. It does this through analyzing personal journal entries using machine learning, and then privately responding to the author with proper guidance. In this thesis, we focus on determining the feasibility and usefulness of the machine learning models that drive ALJI. With heavy data limitations, we cautiously report that with a single journal entry, our model detects when a person's symptoms warrant professional intervention with a 61% accuracy. A great amount of discussion on the proposed solution, methods, results, and future directions of ALJI is included.
  • Thumbnail Image
    Amplifying the Griot: Technology for Preserving, Retelling, and Supporting Underrepresented Stories
    Kotut, Lindah Jerop (Virginia Tech, 2021-05-24)
    As we develop intelligent systems to handle online interactions and digital stories, how do we address those stories that are unwritten and invisible? How do ensure that communities who value oral histories are not left behind, and their voices also inform the design of these systems? How do we determine that the technology we design respect the agency and ownership of the stories, without imposing our own biases? To answer these questions, I rely on accounts from different underrepresented communities, as avenues to examine how digital technology affect their stories, and the agency they have over them. From these stories, I elicit guidelines for the design of equitable and resilient tools and technologies. I sought wisdom from griots who are master storytellers and story-keepers on the craft of handling both written and unwritten stories, which instructed the development of the Respectful Space for technology typology, a framework that informs our understanding and interaction with underrepresented stories. The framework guided the approach to understand technology use by inhabitants of rural spaces in the United States--particularly long-distance hikers who traverse these spaces. I further discuss the framework's extensibility, by considering its use for community self-reflection, and for researchers to query the ethical implications of their research, the technology they develop, and the consideration for the voices that the technology amplifies or suppresses. The intention is to highlight the vast resources that exist in domains we do not consider, and the importance of the underrepresented voices to also inform the future of technology.
  • Thumbnail Image
    Assessing enactment of content regulation policies: A post hoc crowd-sourced audit of election misinformation on YouTube
    Juneja, Prerna; Bhuiyan, Md Momen; Mitra, Tanushree (ACM, 2023-04-19)
    With the 2022 US midterm elections approaching, conspiratorial claims about the 2020 presidential elections continue to threaten users’ trust in the electoral process. To regulate election misinformation, YouTube introduced policies to remove such content from its searches and recommendations. In this paper, we conduct a 9-day crowd-sourced audit on YouTube to assess the extent of enactment of such policies. We recruited 99 users who installed a browser extension that enabled us to collect up-next recommendation trails and search results for 45 videos and 88 search queries about the 2020 elections. We find that YouTube’s search results, irrespective of search query bias, contain more videos that oppose rather than support election misinformation. However, watching misinformative election videos still lead users to a small number of misinformative videos in the up-next trails. Our results imply that while YouTube largely seems successful in regulating election misinformation, there is still room for improvement.
  • Thumbnail Image
    Combating Problematic Information Online with Dual Process Cognitive Affordances
    Bhuiyan, MD Momen (Virginia Tech, 2023-08-04)
    Dual process theories of mind have been developed over the last decades to posit that humans use heuristics or mental shortcuts (automatic) and analytical (reflective) reasoning while consuming information. Can such theories be used to support users' information consumption in the presence of problematic content in online spaces? To answer, I merge these theories with the idea of affordances from HCI to into the concept of dual process cognitive affordances, consisting of automatic affordance and reflective affordance. Using this concept, I built and tested a set of systems to address two categories of online problematic content: misinformation and filter bubbles. In the first system, NudgeCred, I use cognitive heuristics from the MAIN model to design automatic affordances for better credibility assessment of news tweets from mainstream and misinformative sources. In TransparencyCue, I show the promise of value-centered automatic affordance design inside news articles differentiating content quality. To encourage information consumption outside their ideological filter bubble, in NewsComp, I use comparative annotation to design reflective affordances that enable active engagement with stories from opposing-leaning sources. In OtherTube, I use parasocial interaction, that is, experiencing information feed through the eyes of someone else, to design a reflective affordance that enables recognition of filter bubbles in their YouTube recommendation feeds. Each system shows various degrees of success and outlines considerations in cognitive affordances design. Overall, this thesis showcases the utility of design strategies centered on dual process information cognition model of human mind to combat problematic information space.
  • Thumbnail Image
    Design guidelines for narrative maps in sensemaking tasks
    Norambuena, Brian Felipe Keith; Mitra, Tanushree; North, Christopher L. (SAGE, 2022-03-02)
    Narrative sensemaking is a fundamental process to understand sequential information. Narrative maps are a visual representation framework that can aid analysts in their narrative sensemaking process. Narrative maps allow analysts to understand the big picture of a narrative, uncover new relationships between events, and model the connection between storylines. We seek to understand how analysts create and use narrative maps in order to obtain design guidelines for an interactive visualization tool for narrative maps that can aid analysts in narrative sensemaking. We perform two experiments with a data set of news articles. The insights extracted from our studies can be used to design narrative maps, extraction algorithms, and visual analytics tools to support the narrative sensemaking process. The contributions of this paper are three-fold: (1) an analysis of how analysts construct narrative maps; (2) a user evaluation of specific narrative map features; and (3) design guidelines for narrative maps. Our findings suggest ways for designing narrative maps and extraction algorithms, as well as providing insights toward useful interactions. We discuss these insights and design guidelines and reflect on the potential challenges involved. As key highlights, we find that narrative maps should avoid redundant connections that can be inferred by using the transitive property of event connections, reducing the overall complexity of the map. Moreover, narrative maps should use multiple types of cognitive connections between events such as topical and causal connections, as this emulates the strategies that analysts use in the narrative sensemaking process.
  • Thumbnail Image
    Human Behavior Modeling and Calibration in Epidemic Simulations
    Singh, Meghendra (Virginia Tech, 2019-01-25)
    Human behavior plays an important role in infectious disease epidemics. The choice of preventive actions taken by individuals can completely change the epidemic outcome. Computational epidemiologists usually employ large-scale agent-based simulations of human populations to study disease outbreaks and assess intervention strategies. Such simulations rarely take into account the decision-making process of human beings when it comes to preventive behaviors. Absence of realistic agent behavior can undermine the reliability of insights generated by such simulations and might make them ill-suited for informing public health policies. In this thesis, we address this problem by developing a methodology to create and calibrate an agent decision-making model for a large multi-agent simulation, in a data driven way. Our method optimizes a cost vector associated with the various behaviors to match the behavior distributions observed in a detailed survey of human behaviors during influenza outbreaks. Our approach is a data-driven way of incorporating decision making for agents in large-scale epidemic simulations.
  • 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.
  • Thumbnail Image
    Mixed Multi-Model Semantic Interaction for Graph-based Narrative Visualizations
    Norambuena, Brian Felipe Keith; Mitra, Tanushree; North, Christopher L. (ACM, 2023-03-27)
    Narrative sensemaking is an essential part of understanding sequential data. Narrative maps are a visual representation model that can assist analysts to understand narratives. In this work, we present a semantic interaction (SI) framework for narrative maps that can support analysts through their sensemaking process. In contrast to traditional SI systems which rely on dimensionality reduction and work on a projection space, our approach has an additional abstraction layer—the structure space—that builds upon the projection space and encodes the narrative in a discrete structure. This extra layer introduces additional challenges that must be addressed when integrating SI with the narrative extraction pipeline. We address these challenges by presenting the general concept of Mixed Multi-Model Semantic Interaction (3MSI)—an SI pipeline, where the highest-level model corresponds to an abstract discrete structure and the lower-level models are continuous. To evaluate the performance of our 3MSI models for narrative maps, we present a quantitative simulation-based evaluation and a qualitative evaluation with case studies and expert feedback. We find that our SI system can model the analysts’ intent and support incremental formalism for narrative maps.
  • Thumbnail Image
    Narrative Maps: A Computational Model to Support Analysts in Narrative Sensemaking
    Keith Norambuena, Brian Felipe (Virginia Tech, 2023-08-08)
    Narratives are fundamental to our understanding of the world, and they are pervasive in all activities that involve representing events in time. Narrative analysis has a series of applications in computational journalism, intelligence analysis, and misinformation modeling. In particular, narratives are a key element of the sensemaking process of analysts. In this work, we propose a narrative model and visualization method to aid analysts with this process. In particular, we propose the narrative maps framework—an event-based representation that uses a directed acyclic graph to represent the narrative structure—and a series of empirically defined design guidelines for map construction obtained from a user study. Furthermore, our narrative extraction pipeline is based on maximizing coherence—modeled as a function of surface text similarity and topical similarity—subject to coverage—modeled through topical clusters—and structural constraints through the use of linear programming optimization. For the purposes of our evaluation, we focus on the news narrative domain and showcase the capabilities of our model through several case studies and user evaluations. Moreover, we augment the narrative maps framework with interactive AI techniques—using semantic interaction and explainable AI—to create an interactive narrative model that is capable of learning from user interactions to customize the narrative model based on the user's needs and providing explanations for each core component of the narrative model. Throughout this process, we propose a general framework for interactive AI that can handle similar models to narrative maps—that is, models that mix continuous low-level representations (e.g., dimensionality reduction) with more abstract high-level discrete structures (e.g., graphs). Finally, we evaluate our proposed framework through an insight-based user study. In particular, we perform a quantitative and qualitative assessment of the behavior of users and explore their cognitive strategies, including how they use the explainable AI and semantic interaction capabilities of our system. Our evaluation shows that our proposed interactive AI framework for narrative maps is capable of aiding users in finding more insights from data when compared to the baseline.
  • Thumbnail Image
    NewsComp: Facilitating Diverse News Reading through Comparative Annotation
    Bhuiyan, Md Momen; Lee, Sang Won; Goyal, Nitesh; Mitra, Tanushree (ACM, 2023-04-19)
    To support efficient, balanced news consumption, merging articles from diverse sources into one, potentially through crowdsourcing, could alleviate some hurdles. However, the merging process could also impact annotators’ attitudes towards the content. To test this theory, we propose comparative news annotation; that is, annotating similarities and differences between a pair of articles. By developing and deploying NewsComp—a prototype system—we conducted a between-subjects experiment (N = 109) to examine how users’ annotations compare to experts’, and how comparative annotation affects users’ perceptions of article credibility and quality. We found that comparative annotation can marginally impact users’ credibility perceptions in certain cases; it did not impact perceptions of quality. While users’ annotations were not on par with experts’, they showed greater precision in finding similarities than in identifying disparate important statements. The comparison process also led users to notice differences in information placement and depth, degree of factuality/opinion, and empathetic/inflammatory language use. We discuss implications for the design of future comparative annotation tasks.
  • Thumbnail Image
    Online Social Deception and Its Countermeasures: A Survey
    Guo, Zhen; Cho, Jin-Hee; Chen, Ing-Ray; Sengupta, Srijan; Hong, Michin; Mitra, Tanushree (2021-01-05)
    We are living in an era when online communication over social network services (SNSs) have become an indispensable part of people's everyday lives. As a consequence, online social deception (OSD) in SNSs has emerged as a serious threat in cyberspace, particularly for users vulnerable to such cyberattacks. Cyber attackers have exploited the sophisticated features of SNSs to carry out harmful OSD activities, such as financial fraud, privacy threat, or sexual/labor exploitation. Therefore, it is critical to understand OSD and develop effective countermeasures against OSD for building trustworthy SNSs. In this paper, we conduct an extensive survey, covering 1) the multidisciplinary concept of social deception; 2) types of OSD attacks and their unique characteristics compared to other social network attacks and cybercrimes; 3) comprehensive defense mechanisms embracing prevention, detection, and response (or mitigation) against OSD attacks along with their pros and cons; 4) datasets/metrics used for validation and verification; and 5) legal and ethical concerns related to OSD research. Based on this survey, we provide insights into the effectiveness of countermeasures and the lessons learned from the existing literature. We conclude our survey with in-depth discussions on the limitations of the state-of-the-art and suggest future research directions in OSD research.
  • Thumbnail Image
    OtherTube: Facilitating Content Discovery and Reflection by Exchanging YouTube Recommendations with Strangers
    Bhuiyan, Md Momen; Bautista Isaza, Carlos Augusto; Mitra, Tanushree; Lee, Sang Won (ACM, 2022-04-29)
    To promote engagement, recommendation algorithms on platforms like YouTube increasingly personalize users’ feeds, limiting users’ exposure to diverse content and depriving them of opportunities to refect on their interests compared to others’. In this work, we investigate how exchanging recommendations with strangers can help users discover new content and refect.We tested this idea by developing OtherTube—a browser extension for YouTube that displays strangers’ personalized YouTube recommendations. OtherTube allows users to (i) create an anonymized profle for social comparison, (ii) share their recommended videos with others, and (iii) browse strangers’ YouTube recommendations.We conducted a 10-day-long user study (n = 41) followed by a post-study interview (n = 11). Our results reveal that users discovered and developed new interests from seeing OtherTube recommendations. We identifed user and content characteristics that afect interaction and engagement with exchanged recommendations; for example, younger users interacted more with OtherTube, while the perceived irrelevance of some content discouraged users from watching certain videos. Users refected on their interests as well as others’, recognizing similarities and diferences. Our work shows promise for designs leveraging the exchange of personalized recommendations with strangers.
  • Thumbnail Image
    Role of Social Media and Computing in Organizations aiding Asylum Seekers and Undocumented Migrants in the United States
    Rama Subramanian, Deepika (Virginia Tech, 2020-09-03)
    Every year, an increasing number of displaced people arrive at the United States of America's border to request asylum. Several groups are working to help migrants by providing them with essential items and services, housing, and legal advice. Drawing on ethnographic findings, this work presents a situated perspective of how citizen responders utilize technological systems to provide relief to those affected by the immigration crisis. Often, these citizens with common goals come together to form organizations. This study investigates how social media and technology support on-the-ground work, advocacy work, care-work, and invisible work of these organizations. Further, I highlight how technological systems fail organizations and how the emergence of care-work replaced these systems. Finally, I make design recommendations to social media and technological systems' design to boost the efficacy of collective crisis response by citizens.
  • Thumbnail Image
    Seeing the Forest for the Trees: New approaches to Characterizing and Forecasting Cascades
    Krishnan, Siddharth (Virginia Tech, 2018-05-18)
    Cascades are a popular construct to observe and study information propagation (or diffusion) in social media such as Twitter and are defined using notions of influence, activity, or discourse commonality (e.g., hashtags). While these notions of cascades lead to different perspectives, primarily cascades are modeled as trees. We argue in this thesis an alternative viewpoint of cascades as forests (of trees) which yields a richer vocabulary of features to understand information propagation. We propose to develop a framework to extract forests and analyze their growth by studying their evolution at the tree-level and at the node-level. Furthermore, we outline four different problems that use the forest framework. First, we show that such forests of information cascades can be used to design counter-contagion algorithms to disrupt the spread of negative campaigns or rumors. Secondly, we demonstrate how such forests of information cascades can give us a rich set of features (structural and temporal), which can be used to forecast information flow. Thirdly, we argue that cascades modeled as forests can help us glean social network sensors to detect future contagious outbreaks that occur in the social network. To conclude, we show preliminary results of an approach - a generative model, that can describe information cascades modeled as forests and can generate synthetic cascades with empirical properties mirroring cascades extracted from Twitter.
  • Thumbnail Image
    Supporting and Transforming High-Stakes Investigations with Expert-Led Crowdsourcing
    Venkatagiri, Sukrit (Virginia Tech, 2022-12-20)
    Expert investigators leverage their advanced skills and deep experience to solve complex investigations, but they face limits on their time and attention. In contrast, crowds of novices can be highly scalable and parallelizable, but lack expertise and may engage in vigilante behavior. In this dissertation, I introduce and evaluate the framework of expert-led crowdsourcing through three studies across two domains, journalism and law enforcement. First, through an ethnographic study of two law enforcement murder investigations, I uncover tensions in a real-world crowdsourced investigation and introduce the expert-led crowdsourcing framework. Second, I instantiate expert-led crowdsourcing in two collaboration systems: GroundTruth and CuriOSINTy. GroundTruth is focused on one specific investigative task, image geolocation. CuriOSINTy expands the flexibility and scope of expert-led crowdsourcing to handle more complex and multiple investigative tasks: identifying and debunking misinformation. Third, I introduce a framework for understanding how expert-led crowdsourced investigations work and how to better support them. Finally, I conclude with a discussion of how expert-led crowdsourcing enables experts and crowds to do more than either could alone, as well as how it can be generalized to other domains.
  • Thumbnail Image
    A Survey on Event-based News Narrative Extraction
    Norambuena, Brian Felipe Keith; Mitra, Tanushree; North, Christopher L. (ACM, 2023-03)
    Narratives are fundamental to our understanding of the world, providing us with a natural structure for knowledge representation over time. Computational narrative extraction is a subfield of artificial intelligence that makes heavy use of information retrieval and natural language processing techniques. Despite the importance of computational narrative extraction, relatively little scholarly work exists on synthesizing previous research and strategizing future research in the area. In particular, this article focuses on extracting news narratives from an event-centric perspective. Extracting narratives from news data has multiple applications in understanding the evolving information landscape. This survey presents an extensive study of research in the area of event-based news narrative extraction. In particular, we screened over 900 articles that yielded 54 relevant articles. These articles are synthesized and organized by representation model, extraction criteria, and evaluation approaches. Based on the reviewed studies, we identify recent trends, open challenges, and potential research lines.
  • Thumbnail Image
    Understanding Challenges of Online Group Chat for Productive Discourse at Scale
    Pasad, Viral Shrikant (Virginia Tech, 2020-09-14)
    Group chat facilitates remote collaboration and idea exchanges. With the widespread use of group chat for productive information exchanges, it becomes dicult for members of groups to keep up and stay grounded during the long stream of conversation that is generated. I conducted a need-finding study where I simulated group chat conversations in the context of collaboration to learn about issues and behaviors in a group chat when the size of the group chat is 5 or 10. The study participants also filled out a survey post the group chat, describing their challenges and issues with the group chat. A grounded theory approach analyses of the data collected, and the chat conversation gave us several themes. Our results show that participants generally felt that there were too many messages. A majority of the participants found it was hard to keep track of what was happening. Information overload is a significant challenge that creates several other challenges for the participants, such as missed messages, redundant messages, wasted e↵orts, and diculty in gathering consensus. I observed some behaviors such as broken utterances and other strategies employed by participants when overwhelmed with the high activity. I use this knowledge to motivate recommendations and suggestions for future redesigns and development of this indispensable tool of the workforce