Advanced Topics in Human-Computer Interaction

This course of Advanced Topics in HCI emphasizes discussions and explorations on human-AI interaction with reading a set of representative papers published in the field of HCI, and creation as well as prototyping human-AI interaction systems. Students lead their own capstone projects where they build interactive systems and present their demonstrations at the last class.

This course is double-listed as “3747-108: Advanced Topics in HCI” in Graduate School of Engineering and “4915100: Human Interfaces” in Interfaculty Initiative in Information Studies, Graduate School of Interdisciplinary Information Studies. Students are allowed to register only to either of these two courses. Everything besides a course name is the same, so no worries about which one you should register. :)

この講義は工学系では「3747-108: ヒューマンコンピュータインタラクション特論」，情報学環・学際情報学府では「4915100: ヒューマンインタフェース」として提供されています．学生はどちらかの講義にしか登録できません．講義の名前以外はすべて同じですので，どちらかで登録していただければ結構です．:)

This course has two major objectives: getting familiarized with classic and recent HCI research that well demonstrates novel interactive systems and applications, and prototyping an interactive system. To achieve them, this course offers a mixture of research discussions on HCI papers and capstone projects.

• Research discussions: We discuss a selected set of papers published at HCI and its relevant conferences, such as CHI, UIST, UbiComp, CSCW, and MobiSys. Each student will be asked to lead discussions at least once during the semester. This year, we mostly focus on various sensing technology and its interactive applications.
• Capstone projects: Students conduct a project to develop an interactive system using sensors and/or hardware.

Except the first and last classes, the rough class structure is as follows:

• A brief introduction from the instructor
• 35 mins * 2: Paper discussions
  • 15 mins presentation by a discussion chair
  • 20 mins discussion among students and the instructor
• Wrap-up
• Discussions for individual capstone projects

English is the official language in this course though Japanese may be used if necessary. All teaching is done in English at a class. Students are strongly recommended to deliver their presentations and demonstrations in English. You may use Japanese when you have large difficulties in communication, but you must always try your best to speak English.

We do not have any explicit prerequisite for this course, but students are expected to have:

• Basic knowledge and experience on HCI research,
• Programming skills and experience, and
• English communication skills.

But, the most important is, of course, your strong passion. :)

We have no tolerance to any type of academic misconducts, such as plagiarism, inappropriate citations, and fabrications. Examples are:

• Using others' ideas without appropriate citations and/or acknowledgements,
• Using codes and/or libraries without citing appropriately,
• Using source codes written by others without explicit permissions，and
• Making up data or system behavior for better-looking demonstration.

In case serious academic misconducts are found, we give following strong penalties depending on their significance.

• No mark for assignments where academic misconducts are found (Marked as zero. Marks are retracted if already given),
• No mark for all assignments that have been already submitted,
• No mark for all assignments that have been already submitted and prohibition to submit future assignments.

Please make sure that your reports and source codes do not cause misunderstandings.

Auditing students are welcome to join us. But I strongly recommend you to do a discussion chair even if you are just auditing. Also participate in discussions at the class. Just don't be a free rider. :)

Your performance in this course will be evaluated in the following criteria.

• [30%] Paper discussion: Given to your performance in leading discussions about the paper assigned to you from the reading list.
• [50%] Capstone project: Given to the quality of your project proposal (and prototype demonstration if you have any).
• [20%] Engagement and attendance: Given to your attendance to the course and your involvement in discussions during the class.

You must both do a discussion chair at least once and complete your capstone project to get a final mark. Otherwise, your mark will be zero.

Please submit your paper preference from the following Google Form page by 14th April.

https://forms.gle/PF3zYFD8gokcpYR16

• Decision making
  • Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, and Gagan Bansal. 2023. Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations. Proc. ACM Hum.-Comput. Interact. 7, CSCW2, Article 370 (October 2023), 32 pages. https://doi.org/10.1145/3610219
  • Chun-Wei Chiang, Zhuoran Lu, Zhuoyan Li, and Ming Yin. 2024. Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil's Advocate. In Proceedings of the 29th International Conference on Intelligent User Interfaces (IUI '24). Association for Computing Machinery, New York, NY, USA, 103–119. https://doi.org/10.1145/3640543.3645199
• Writing with AI
  • Maurice Jakesch, Advait Bhat, Daniel Buschek, Lior Zalmanson, and Mor Naaman. 2023. Co-Writing with Opinionated Language Models Affects Users’ Views. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 111, 1–15. https://doi.org/10.1145/3544548.3581196
  • Fiona Draxler, Anna Werner, Florian Lehmann, Matthias Hoppe, Albrecht Schmidt, Daniel Buschek, and Robin Welsch. 2024. The AI Ghostwriter Effect: When Users do not Perceive Ownership of AI-Generated Text but Self-Declare as Authors. ACM Trans. Comput.-Hum. Interact. 31, 2, Article 25 (April 2024), 40 pages. https://doi.org/10.1145/3637875
• Design guidelines and evaluations
  • Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for Human-AI Interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19). Association for Computing Machinery, New York, NY, USA, Paper 3, 1–13. https://doi.org/10.1145/3290605.3300233
  • Bansal, G., Nushi, B., Kamar, E., Lasecki, W.S., Weld, D.S. and Horvitz, E. 2019. Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance. Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 7, 1 (Oct. 2019), 2-11. DOI:https://doi.org/10.1609/hcomp.v7i1.5285
• Social media and AI
  • Nikhil Sharma, Q. Vera Liao, and Ziang Xiao. 2024. Generative Echo Chamber? Effect of LLM-Powered Search Systems on Diverse Information Seeking. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 1033, 1–17. https://doi.org/10.1145/3613904.3642459
  • Thitaree Tanprasert, Sidney S Fels, Luanne Sinnamon, and Dongwook Yoon. 2024. Debate Chatbots to Facilitate Critical Thinking on YouTube: Social Identity and Conversational Style Make A Difference. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 805, 1–24. https://doi.org/10.1145/3613904.3642513
• AI-medicated communication
  • Ziyi Liu, Zhengzhe Zhu, Lijun Zhu, Enze Jiang, Xiyun Hu, Kylie A Peppler, and Karthik Ramani. 2024. ClassMeta: Designing Interactive Virtual Classmate to Promote VR Classroom Participation. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 659, 1–17. https://doi.org/10.1145/3613904.3642947
  • Kowe Kadoma, Marianne Aubin Le Quere, Xiyu Jenny Fu, Christin Munsch, Danaë Metaxa, and Mor Naaman. 2024. The Role of Inclusion, Control, and Ownership in Workplace AI-Mediated Communication. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 1016, 1–10. https://doi.org/10.1145/3613904.3642650
• Generative AI in workplace
  • Charlotte Kobiella, Yarhy Said Flores López, Franz Waltenberger, Fiona Draxler, and Albrecht Schmidt. 2024. “If the Machine Is As Good As Me, Then What Use Am I?” – How the Use of ChatGPT Changes Young Professionals' Perception of Productivity and Accomplishment. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 1018, 1–16. https://doi.org/10.1145/3613904.3641964
  • Allison Woodruff, Renee Shelby, Patrick Gage Kelley, Steven Rousso-Schindler, Jamila Smith-Loud, and Lauren Wilcox. 2024. How Knowledge Workers Think Generative AI Will (Not) Transform Their Industries. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 641, 1–26. https://doi.org/10.1145/3613904.3642700
• Avoiding over-reliance on AI
  • Zana Buçinca, Maja Barbara Malaya, and Krzysztof Z. Gajos. 2021. To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making. Proc. ACM Hum.-Comput. Interact. 5, CSCW1, Article 188 (April 2021), 21 pages. https://doi.org/10.1145/3449287
  • Valdemar Danry, Pat Pataranutaporn, Yaoli Mao, and Pattie Maes. 2023. Don’t Just Tell Me, Ask Me: AI Systems that Intelligently Frame Explanations as Questions Improve Human Logical Discernment Accuracy over Causal AI explanations. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 352, 1–13. https://doi.org/10.1145/3544548.3580672
• Creativity and uncreativity
  • Yiren Liu, Si Chen, Haocong Cheng, Mengxia Yu, Xiao Ran, Andrew Mo, Yiliu Tang, and Yun Huang. 2024. How AI Processing Delays Foster Creativity: Exploring Research Question Co-Creation with an LLM-based Agent. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 17, 1–25. https://doi.org/10.1145/3613904.3642698
  • Samangi Wadinambiarachchi, Ryan M. Kelly, Saumya Pareek, Qiushi Zhou, and Eduardo Velloso. 2024. The Effects of Generative AI on Design Fixation and Divergent Thinking. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 380, 1–18. https://doi.org/10.1145/3613904.3642919
• Kids and AI
  • Yoonjoo Lee, Tae Soo Kim, Sungdong Kim, Yohan Yun, and Juho Kim. 2023. DAPIE: Interactive Step-by-Step Explanatory Dialogues to Answer Children’s Why and How Questions. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI '23). Association for Computing Machinery, New York, NY, USA, Article 450, 1–22. https://doi.org/10.1145/3544548.3581369
  • Chao Zhang, Xuechen Liu, Katherine Ziska, Soobin Jeon, Chi-Lin Yu, and Ying Xu. 2024. Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24). Association for Computing Machinery, New York, NY, USA, Article 274, 1–23. https://doi.org/10.1145/3613904.3642647
• Trustworthiness
  • Pataranutaporn, P., Liu, R., Finn, E. et al. Influencing human–AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness. Nat Mach Intell 5, 1076–1086 (2023). https://doi.org/10.1038/s42256-023-00720-7
  • Thomas H. Costello et al. ,Durably reducing conspiracy beliefs through dialogues with AI.Science385,eadq1814(2024). https://www.science.org/doi/10.1126/science.adq1814

In research discussions, we discuss some of recently-published HCI work that demonstrates strong novelty and/or progress in this field. After the first class, please name your preferences in this page.

• Discussion chair: This person plays a central role of stimulating discussions among fellow students. You will have 20 - 25 minutes in total for your discussion slot. You must read the assigned paper carefully, and deliver a 10-minute presentation. After your presentation, you will be expected to lead discussions with fellow students. Your presentation material must be in English though you can deliver either in English or Japanese. Your presentation should cover:
  • Backgrounds of the research,
  • Summary of the developed system,
  • Novelty and originality of the work, and
  • pros and cons of the system/method.

• Discussion members: The rest of you will serve as discussion members. You must engage in discussions proactively. All of discussion members must read the papers before coming to the class. You should take notes about your impression on the papers, in particular:
  • What did you like in this work? Why?
  • How do you think this work can inspire your research?
  • What are possible applications out of this technology?
  • What are shortcomings? What improvements do you think this technology needs?
  • If you were a reviewer on this paper, how would you rate and provide feedback?
  • If you were a program committee member and had to pitch this paper to argue accept or reject, how would you do?
  • What impressed you about the writing? What presentation techniques do you think we should learn from the paper?

A capstone project aims to obtain experience of building an interactive system with artificial intelligence, and delivering a live demonstration and demonstrating at least one application scenario. You are asked to build an interactive human-AI system where users play the central role of cognitive tasks, such as decision making, idea/information exploration, productivity/creativity tasks, and critical thinking.

You are encouraged to collaborate with your fellow students and team up for capstone projects. However, your team should be up to three people. Marks for the capstone project will be given equally to all team members.

Your system must be interactive and use some kinds of artificial intelligence. We provide OpenAI API keys if needed.

You also must demonstrate at least one application scenario that involves human higher-order thinking (e.g., decision-making, critical thinking, and creative thinking). Your application does not have to be large-scale or complex, but you have to demonstrate that your system would be something useful to potential users instead of just being cool. Games are not considered as valid applications though gamification for something would be acceptable.

Your system must put users to play the central role of higher-order thinking cognitive tasks. These tasks include decision making, idea/information exploration, productivity/creativity tasks, and critical thinking.

You may take a look at the concept of extraheric AI. Extraheric AI is an human-AI interaction design to foster human higher-order thinking. Please read the following arxiv paper. https://arxiv.org/abs/2409.09218

You will be asked to do a live demonstration at the last class. So make sure that your final system works in real time. Your system will likely to perform some sort of recognition (heuristically or with machine learning). The recognition does not have to be super accurate, but it has to work reasonably well.

We do not care about what programming languages or environment you use. If you need suggestions or support, please consult with the instructor though we do not guarantee providing the stuff you want.

You must deliver the following items at the end of the course.

• Project presentation and live demonstration: Roughly 10 mins presentation. It must include a live demonstration of your system.
• Demonstration video: A video that shows a demonstration of your system. The video can be up to 5 minutes long. MP4 is strongly recommended, but a common video format (e.g., mpeg, avi, wmv, and mov) is also acceptable.

We evaluate your capstone projects in the following criteria:

• [15%] Originality: The uniqueness of your system in terms of the concept, design, and/or implementation.
• [10%] Implementation thoroughness: The quality of your implementation. Note that your implementation does not have to be super robust, but it should be demoable.
• [15%] Application scenario: The practicality of the application scenarios demonstrated.
• [10%] Presentation delivery: The quality of your presentation (including your live demo and video).

Examples of capstone projects are as follows (but not limited to):

• Recognizing user's activities from sensor data on a smartphone
• Detecting gesture input to support a new type of interaction with computers
• Detecting user's different types of physical exercise
• Creating new visual environments for entertainment
• Generating novel output modalities