WhatIf provides an interactive platform for real-time exploration of LLM-driven social simulations, enabling policymakers to iteratively test plans, reflect on assumptions, and uncover vulnerabilities in emergency preparedness scenarios.
mega hub Mixed citations
Using Thematic Analysis in Psychology
Mixed citation behavior. Most common role is method (67%).
38
Pith papers citing it
142.1k
external citations · Crossref
Method
67% of classified citations
hub tools
citation-role summary
method 10
background 5
citation-polarity summary
authors
mega hub controls
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
SoulNote enables multi-session GenAI songwriting for DHH users, producing measurable gains in self-insight, emotion regulation, and self-care attitudes.
A participatory red-teaming project in the Global South created the PLACES dataset of 26k T2I failure examples that reveal unique cultural and linguistic harms missed by existing safety frameworks.
Users entangle their lived experiences with AI predictions in menstrual tracking apps, leading to self-fulfilling prophecies, limited critical awareness from UI, and isolation for non-normative users.
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
LLM-based conversational interface for Android reduces task time and mental effort for blind users versus traditional gesture-based screen readers like TalkBack.
A scoping review and empirical analysis produce a six-category taxonomy of factors driving AI non-development and abandonment, showing that practical issues like resource limits and organizational dynamics often outweigh ethical concerns in real decisions.
AI improves brainstorming quality for general-purpose impact assessment but not specialized applications when it offers hints early and structures ideas later, based on workshop evaluations with 54 participants.
ANVIL automates analogy-based instructional animations for computer science by chaining LLM analogy generation, screenplay structuring, manim code production with repair, and mixed human-automated evaluations.
Interviews with practitioners and educators yield a systematic account of annotation design considerations, trade-offs, and contextual judgments in visualization practice.
A four-year mixed-methods study of game-based systems for Indian CHWs yields eight design guidelines for sustained engagement, learning transfer, and contextual appropriateness in low-resource health training.
StreetDesignAI provides structured multi-persona feedback on cycling designs and a user study shows it broadens designers' grasp of diverse cyclist perspectives and improves design decision confidence.
PREFAB applies preference learning grounded in the peak-end rule to let users annotate only key affective change segments while interpolating the rest, reducing workload and improving confidence in a 25-participant study.
The authors conduct a systematic literature review and real-world analysis to define Crowdsourced Context Systems and map a six-aspect design space with normative implications.
A method merges codebooks via LLM and evaluates human and AI inductive coding with four new metrics on an online conversation dataset.
Longitudinal surveys show AI coding assistants reduce time on code writing but increase supervisory verification tasks, with stable productivity perceptions yet rising reports of worsened developer experience.
Post-editors changed one in three metaphors in NMT and LLM outputs for literary texts, rated quality poor, and found post-editing more laborious than original translation.
GPT produces click distributions significantly different from real humans in 53% of UX first-click tasks, with prompting techniques like personas and chain-of-thought failing to improve alignment.
Teachers disengage from AI agent creation after training due to systemic contradictions that thwart psychological needs rather than skill gaps, and a CHAT-SDT redesign can resolve this by boosting both capacity and willingness.
Cluster analysis of teacher multi-agent workflow designs reveals three archetypes where AI-TPACK emerges dynamically from systems thinking, pedagogical beliefs, and self-efficacy.
PEFT fine-tuning of Code Llama yields feedback on student Java bugs that students judge equal to ChatGPT and better than prompt engineering, using BLEU/ROUGE/BERTScore plus human ratings.
Large-scale review of 5300 AI incident reports shows harms are amplified up to three times at specific intersections including adolescent girls, lower-class people of color, and upper-class political elites.
Trust in social LLM chatbots is a dynamic, situated user state that evolves through ongoing interactions rather than forming as a stable one-time judgment.
AVVA is a new framework adapting verbal analysis for classroom discourse with triangulation across ten steps and a four-criterion validation scheme for temporal stability, applied to 23 hours of recordings.
citing papers explorer
-
"It became a self-fulfilling prophecy": How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps
Users entangle their lived experiences with AI predictions in menstrual tracking apps, leading to self-fulfilling prophecies, limited critical awareness from UI, and isolation for non-normative users.
-
Beyond Community Notes: A Framework for Understanding and Building Crowdsourced Context Systems for Social Media
The authors conduct a systematic literature review and real-world analysis to define Crowdsourced Context Systems and map a six-aspect design space with normative implications.
-
Fine-Tuning Models for Automated Code Review Feedback
PEFT fine-tuning of Code Llama yields feedback on student Java bugs that students judge equal to ChatGPT and better than prompt engineering, using BLEU/ROUGE/BERTScore plus human ratings.
-
Not a Collaborator or a Supervisor, but an Assistant: Striking the Balance Between Efficiency and Ownership in AI-incorporated Qualitative Data Analysis
Interviews with 16 qualitative researchers identify efficiency, ownership, and trust as key factors shaping preferences for AI as a supportive assistant rather than a full collaborator or supervisor in qualitative data analysis.