Researcher profile

Prerna Juneja

Prerna Juneja contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Human-Computer Interaction Computation and Language cs.CY

Trust snapshot

Quick read

Trust 17 - UnverifiedVerification L1Unclaimed author

4works

0followers

3topics

2close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations

There are growing concerns about the risks posed by AI companion applications designed for emotional engagement. Existing safety evaluations often rely on self-reported user data or interviews, offering limited insights into real-time dynamics. We present the first end-to-end scalable framework for controlled simulation and safety evaluation of multi-turn interactions with AI companion applications. Our framework integrates four key components: persona construction with clinical and psychometric validation, persona-specific scenario generation, scenario-driven multi-turn simulation with a dialogue refinement module that preserves persona fidelity, and harm evaluation. We apply this framework to evaluate how Replika, a widely used AI companion app, responds to high-risk user groups. We construct 9 personas representing individuals with depression, anxiety, PTSD, eating disorders, and incel identity, and collect 1,674 dialogue pairs across 25 high-risk scenarios. We combine emotion modeling and LLM-assisted utterance-and harm-level classification to analyze these exchanges. Results show that Replika exhibits a narrow emotional range dominated by curiosity and care, while frequently mirroring or normalizing unsafe content such as self-harm, disordered eating, and violent-fantasy narratives. These findings highlight how controlled persona simulations can serve as a scalable testbed for evaluating safety risks in AI companions.

preprint2022arXiv

Algorithmic nudge to make better choices: Evaluating effectiveness of XAI frameworks to reveal biases in algorithmic decision making to users

In this position paper, we propose the use of existing XAI frameworks to design interventions in scenarios where algorithms expose users to problematic content (e.g. anti vaccine videos). Our intervention design includes facts (to indicate algorithmic justification of what happened) accompanied with either fore warnings or counterfactual explanations. While fore warnings indicate potential risks of an action to users, the counterfactual explanations will indicate what actions user should perform to change the algorithmic outcome. We envision the use of such interventions as `decision aids' to users which will help them make informed choices.

preprint2022arXiv

Human and technological infrastructures of fact-checking

Increasing demands for fact-checking has led to a growing interest in developing systems and tools to automate the fact-checking process. However, such systems are limited in practice because their system design often does not take into account how fact-checking is done in the real world and ignores the insights and needs of various stakeholder groups core to the fact-checking process. This paper unpacks the fact-checking process by revealing the infrastructures -- both human and technological -- that support and shape fact-checking work. We interviewed 26 participants belonging to 16 fact-checking teams and organizations with representation from 4 continents. Through these interviews, we describe the human infrastructure of fact-checking by identifying and presenting, in-depth, the roles of six primary stakeholder groups, 1) Editors, 2) External fact-checkers, 3) In-house fact-checkers, 4) Investigators and researchers, 5) Social media managers, and 6) Advocators. Our findings highlight that the fact-checking process is a collaborative effort among various stakeholder groups and associated technological and informational infrastructures. By rendering visibility to the infrastructures, we reveal how fact-checking has evolved to include both short-term claims centric and long-term advocacy centric fact-checking. Our work also identifies key social and technical needs and challenges faced by each stakeholder group. Based on our findings, we suggest that improving the quality of fact-checking requires systematic changes in the civic, informational, and technological contexts.

preprint2021arXiv

Auditing E-Commerce Platforms for Algorithmically Curated Vaccine Misinformation

There is a growing concern that e-commerce platforms are amplifying vaccine-misinformation. To investigate, we conduct two-sets of algorithmic audits for vaccine misinformation on the search and recommendation algorithms of Amazon -- world's leading e-retailer. First, we systematically audit search-results belonging to vaccine-related search-queries without logging into the platform -- unpersonalized audits. We find 10.47% of search-results promote misinformative health products. We also observe ranking-bias, with Amazon ranking misinformative search-results higher than debunking search-results. Next, we analyze the effects of personalization due to account-history, where history is built progressively by performing various real-world user-actions, such as clicking a product. We find evidence of filter-bubble effect in Amazon's recommendations; accounts performing actions on misinformative products are presented with more misinformation compared to accounts performing actions on neutral and debunking products. Interestingly, once user clicks on a misinformative product, homepage recommendations become more contaminated compared to when user shows an intention to buy that product.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint