Designing AI-Infused Interactive Systems for Online Communities: A Systematic Literature Review

Yuanhao Zhang, Xiaoyu Wang, Jiaxiong Hu, Ziqi Pan, Zhenhui Peng and Xiaojuan Ma

• We present a systematic review of 77 studies, analyzing the systems they propose through three lenses: the challenges they aim to address, their design functionalities, and the evaluation strategies employed.

“Shall We Dig Deeper?”: Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussions

Yuanhao Zhang, Wenbo Li, Xiaoyu Wang, Kangyu Yuan, Shuai Ma, and Xiaojuan Ma

• We explored AI intervention strategies (task-oriented and/or relationship-oriented) throughout the knowledge co-construction process, and implemented them in an LLM-powered agent capable of facilitating progression while consolidating foundations at each phase.

CoKnowledge: Supporting Assimilation of Time-synced Collective Knowledge in Online Science Videos

Yuanhao Zhang, Yumeng Wang, Xiyuan Wang, Changyang He, Chenliang Huang, and Xiaojuan Ma

• We developed CoKnowledge — a tool incorporating video abstracts, knowledge graphs, and supplementary danmaku features support viewers’ assimilation of collective knowledge in online science videos.

From Platform Migration to Cultural Integration: the Ingress and Diffusion of #wlw from TikTok to RedNote in Queer Women Communities

Ziqi Pan, Runhua Zhang, Jiehui Luo, Yuanhao Zhang, Yue Deng, and Xiaojuan Ma

• The Western-origin #wlw (womenloving-women) hashtag has risen in the Chinese lesbian community on RedNote. We conducted a two-phase content analysis of #wlw posts, examining different usage patterns during the hashtag’s ingress and diffusion.

” I Love the Internet Again”: Exploring the Interaction Inception of” TikTok Refugees” Flocking into RedNote

Kangyu Yuan, Li Zhang, Hanfang, Lyu, Ziqi Pan, Yuanhao Zhang, Junze Li, Bingcan Guo, Jiaxiong Hu, Qingyu Guo, and Xiaojuan Ma

• The U.S. government’s announcement to ban TikTok in January 2025 led an influx of TikTok users to migrate to RedNote, a Chinese user dominant social media platform. In this study, we analyze 3,510 RedNote posts to characterize how TikTok migrants blend into the platform.

DBox: Scaffolding Algorithmic Programming Learning through Learner-LLM Co-Decomposition

Shuai Ma, Junling Wang, Yuanhao Zhang, Xiaojuan Ma, and April Wang

• We introduced Decomposition Box (DBox), an LLM-based interactive system that scaffolds and adapts to learners’ personalized construction of a step tree by providing just the right level of support.

Be There, Be Fun, Be Streamed! Designing Interactive AR Scenic Live-Streaming.

Zeyu Huang, Zuyu Xu, Yuanhao Zhang, Chengzhong Liu, Yanwei Zhao, Chuhan Shi, Chen Zhao, and Xiaojuan Ma

• We propose a medium called Augmented Reality Scenic Live-Streaming (ARSLS), where additional virtual content is superimposed and integrated into the real-world scene to actualize proper audience interactions in scenic-oriented live streams.

DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration

Chengbo Zheng, Yuanhao Zhang, Zeyu Huang, Chuhan Shi, Minrui Xu, and Xiaojuan Ma

• We introduce DiscipLink, a novel interactive system that facilitates collaboration between researchers and large language models (LLMs) in interdisciplinary information seeking (IIS).

Sharing Frissons among Online Video Viewers: Exploring the Design of Affective Communication for Aesthetic Chills

Zeyu Huang, Xinyi Cao, Yuanhao Zhang, and Xiaojuan Ma.

• We propose an afective communication approach on online video platforms that senses, aggregates, and presents viewers’ frissons while watching videos asynchronously.

Exploring the Effects of Self-Mockery to Improve Task-Oriented Chatbot’s Social Intelligence

Chengzhong Liu, Shixu Zhou, Yuanhao Zhang, Shixu Zhou, Dingdong Liu, Zhenhui Peng, and Xiaojuan Ma.

• We proposed to apply self-mockery humor to a customer service chatbot in different interaction stages with users to improve chatbots’ overall social intelligence.

When Gamification Spoils Your Learning: A Qualitative Case Study of Gamification Misuse in a Language-LearningApp

Reza Hadi Mogavi, Bingcan Guo, Yuanhao Zhang, Ehson UI Haq, Pan Hui, and Xiaojuan Ma.

• We conducted the first extensive qualitative research on gamification misuse in a popular learning app called Duolingo. This study consists of two phases: (I) a content analysis of data from Duolingo forums (from the past nine years) and (II) semi-structured interviews with 15 international Duolingo users.

What Do Users Think of Promotional Gamification Schemes? A Qualitative Case Study in a Question Answering Website

Reza Hadi Mogavi, Yuanhao Zhang, Yongjin Wu, Pan Hui, and Xiaojuan Ma.

• We conduct an extensive qualitative case study of users’ experiences with a promotional gamification scheme on the Community Question Answering Website (CQA) of Stack Exchange, called Winter Bash (WB).