My research area includes Human-Computer Interaction, Human-Centered Artificial Intelligence, and Accessible Computing. I am interested in designing and building AI-powered intelligent user interfaces to provide better human-computer interaction experience to users.
Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a multimodal LLM (e.g., recognition of common meme templates and cultural references) to convey intent, timing, and implicit meaning through conversational interaction. We evaluate MemeBuddy in a user study with 14 blind participants. Results show that dialog-style meme representations consistently improve engagement and user satisfaction compared to caption-style descriptions, while maintaining comparable comprehension.
@inproceedings{bhansali2026memebuddy,title={{M}eme{B}uddy: Dialog-Style Audio Representations for Engaging Non-Visual Meme Experiences},author={Bhansali, Chirag and Ashok, Vikas and Lee, Hae-Na},editor={Choi, Jinho D. and Chen, Yun-Nung and Funakoshi, Kotaro and Emami, Ali},booktitle={Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue},month=aug,year={2026},address={Atlanta, Georgia, USA},publisher={Association for Computational Linguistics},url={https://aclanthology.org/2026.sigdial-1.46/},pages={649--667},}
Inclusive computer literacy education efforts, broadening the participation of blind or visually impaired (BVI) individuals, have gained traction in recent years. Existing literature investigating these efforts primarily draws evidence from affluent Global North contexts, where accessibility resources and legal frameworks are relatively more mature. Little is known about the in-situ teaching and learning challenges faced by trainers and BVI students, respectively, in resource-constrained, multicultural Global South countries like India. To address this knowledge gap, we conducted a four-month contextual inquiry at two computer training centers catering to 94 BVI students in India. We notably observed a rigid, experience-driven training environment and a visually-centric curriculum that discounts the lived experiences of BVI learners and inadvertently undermines their learning self-efficacy. Informed by the findings, we discuss moving beyond functional accessibility-centered teaching toward a more culturally responsive computing pedagogy, facilitated by locally adaptable contextual scaffolds tailored for BVI students in developing societies like India.
@inproceedings{kolgar2026contextual,author={Kolgar Nayak, Akshay and Prakash, Yash and Jayarathna, Sampath and Lee, Hae-Na and Ashok, Vikas},title={Contextual Scaffolding and Self-Efficacy: Supporting Computer Skill Development among Blind Learners in India},year={2026},isbn={9798400722783},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3772318.3791509},doi={10.1145/3772318.3791509},booktitle={Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},articleno={471},numpages={21},keywords={Screen reader, Blind, Visually impaired, Learning, User experience},location={},series={CHI '26},}
