Tianyi Li


About

Tianyi Li (李天一) is an Assistant Professor in the Department of Computer and Information Technology at Purdue University. Her research centers around sensemaking, crowd computing, intelligent user interface, and their applications on human-AI teaming in domain-specific decision making.

Dr. Li designs and develops systems for computer-supported cooperative work. Her research includes crowdsourced sensemaking, to scaffold collective intelligence of novice crowds for tasks such as intelligence analysis. She also conducts research and devise visual analytics tools with user-centered design to combine and coordinate human and artificial intelligence in broader, real-world decision-making processes such as data security and hyperparameter tuning. Throughout her work, Dr. Li investigates and evaluates the UX impact of different Human-AI Interaction patterns.

Dr. Li received her Ph.D. in Computer Science from Virginia Tech, co-advised by Dr. Chris North and Dr. Kurt Luther. Before that, she received her Bachelor's degree from the University of Hong Kong. She also studied at UC San Diego and Shanghai Jiao Tong University as an exchange student.

Previously, Dr. Li was an Assistant Professor in the Department of Computer Science at Loyola University Chicago. She has also worked in the Adaptive Systems and Interaction Group in Microsoft Research AI, the UX team in Cloudera, and Informatica.

News

Nov. 6, 2023 Attended HCOMP and presented our paper at Delft Netherlands.
Nov. 2, 2023 Attended CIRCLS’23 Convening on Shaping AI and Emerging Technologies to Empower Learning Communities and presented a poster on learnersourcing inclusive learning content.
Oct. 16, 2023 Attended CSCW 2023 and Co-organized the Purposeful AI SIG at Minneapolis, MN.
Aug. 7, 2023 My first author paper "Task As Context: A Sensemaking Perspective on Annotating Inter-Dependent Event Attributes With Non-Experts" was accepted by HCOMP 2023.
Jun. 16, 2023 Our Special Interest Group (SIG) on Purposeful AI was accepted by CSCW 2023.
May. 15, 2023 My first author paper "Towards Human-Centered Pavement Quality Annotation with Crowdsourcing" was accepted by the 20th International Conference on Mobile Systems and Pervasive Computing (MobiSPC-2023).
May. 8, 2023 Excited to receive an NSF IUSE award.
Mar. 13, 2023 Virtually attending LAK and presented our workshop paper.
Feb. 11, 2023 Our position paper "Content Moderation and Personalization of Learning Materials with Learnersourcing." was accepted by the Workshop on Partnerships for Cocreating Educational Content, Learning Analytics and Knowledge Conference (LAK 2023).
Feb. 3, 2023 Our demo paper "Event detection explorer: An interactive tool for event detection exploration" was accepted by IUI 2023.

Selected Recent Publications

For full publication list, see my Google Scholar profile


Task As Context: A Sensemaking Perspective on Annotating Inter-dependent Event Attributes with Non-experts Li, Tianyi; Wang, Ping; Shi, Tian; Bian, Yali; Esakia, Andy;
HCOMP 2023
PDFAAAI Proceedings
Purposeful AI Li, Tianyi; Iacobelli, Francisco;
CSCW 2023
PDFACM DLWebsite
Assessing Human-AI Interaction Early Through Factorial Surveys: A Study on the Guidelines for Human-AI Interaction Li, Tianyi; Vorvoreanu, Mihaela; Debellis, Derek; Amershi, Saleema;
TOCHI 2023
PDFACM DLPresentation
Event Detection Explorer: An Interactive Tool for Event Detection Exploration Zhang, Wenlong; Ingale, Bhagyashree; Shabir, Hamza; Li, Tianyi; Shi, Tian; Wang, Ping;
IUI 2023
PDFACM DLDemo
Content Moderation And Personalization Of Learning Materials With Learnersourcing Wang, Ping; Li, Tianyi;
Partnerships For Cocreating Educational Content Workshop At LAK 2023
PDFWorkshop Website
Towards Human-centered Pavement Quality Annotation With Crowdsourcing Li, Tianyi; Surve, Tanmay; Thompson, Eric; Tao, Chengcheng; Bian, Yali;
MobiSPC 2023
PDFElsevier
Toward Systematic Considerations of Missingness in Visual Analytics Sun, Maoyuan; Ma, Yue; Wang, Yuanxin; Li, Tianyi; Zhao, Jian; Liu, Yujun; Zhong, Ping-shou;
VIS 2022
PDFIEEE Xplore
Human-in-the-loop Bias Mitigation In Data Science Pradhan, Romila; Li, Tianyi;
NeurIPS
PDFNeurIPs Workshop Page Poster

Teaching


CNIT 37200 Database Programming
Fall 2023, Spring 2023, Fall 2022, Spring 2022
This course explores advanced database programming techniques for enterprise-wide databases and their implementation. It uses programmatic extensions to Structured Query Language (SQL) supported by today’s enterprise-class Relational Database Management Systems (RDBMS). Topics include advanced data manipulation, storage considerations, data transformation techniques to enhance interoperability of data, stored procedure and trigger design and implementation, and query optimization.
CNIT 581-048 Interactive Systems and Web Development
Spring 2024, Fall 2023, Fall 2022, Fall 2021
This course integrates recent research in human-AI interaction with detailed discussions on web software architecture. Topics include the design and development of web-based user interfaces, databases, and servers. Students will be exposed to and learn how to integrate a wide variety of client- and server-side technologies.
CNIT481-022 Front-End Web Programming
Spring 2024, Spring 2023
The objective of this course is to expose students to the methodology, techniques, design, and evaluation of web-based interfaces. Students will learn and practice design thinking, use HTML, CSS, and JavaScript to create functional, responsive web applications, and get exposure to user experience (UX) design.
COMP 163 Discrete Structures
Fall 2020, Spring 2021
This course covers mathematical proofs and discrete structures, finite automata (mathematical models of computers with finite memory) and context-free grammars and Turing machines (mathematical models of computers with unbounded memory).
COMP 141 Introduction to Computing Tools and Techniques
Spring 2021
This course introduces students to the Unix shell environment and essential tools for succeeding in computer science degrees.

Curriculum Vitae

Previous Projects

  • All
  • CrowdIA
  • Connect the Dots
  • HyperTuner
  • Data-Centric Security
CrowdIA
Solving Mysteries with Crowdsourced Sensemaking
CrowdIA Pipeline:
Video Demo:
Webpage Demo

This project modularized the classical sensemaking loop by Pirolli and Card, by clarifying the inputs and outputs in each of the five components in sensemaking, so that it can be customized to cater different investigation goals and strategies, design and assign specific tasks to crowd workers. The pipeline allows flexible and dynamic implementation of workflows, expert guidance, monitor and feedback. This provide a broader possibility of collaboration among experts, crowds and algorithms.

Related publications:
Connect the Dots
Supporting Intelligence Analysis with Crowdsourcing and Visualization
Crowd-Generated Information Graph:
Video Demo:
Webpage Demo

This project explores how crowdsourcing can be used to help an intelligence analyst find connections within a large body of text-based evidence. For example, an analyst may have access to dozens of evidence documents, and needs to identify a hidden terrorist plot that links the evidence together. We have developed the concept of “context slices,” in which we intelligently divide up large amounts of text so that transient, novice crowd workers can contribute to solving the bigger mystery. From these ideas, we have developed Connect the Dots, a system that uses crowd workers and natural language processing techniques to build an interactive visualization from textual evidence.

Related publications:
HyperTuner
Visual Analytics for Hyperparameter Tuning by Professionals
Hyperparameter Tuning Dashboard:
Video Demo:

While training a machine learning model, data scientists often need to determine some hyperparameters to set up the model. The values of hyperparameters configure the structure and other characteris- tics of the model and can significantly influence the training result. However, given the complexity of the model algorithms and the training processes, identifying a sweet spot in the hyperparameter space for a specific problem can be challenging. This work characterizes user requirements for hyperparameter tuning and proposes a prototype system to provide model-agnostic support. We conducted interviews with data science practitioners in industry to collect user requirements and identify opportunities for leveraging interactive visual support. HyperTuner is a prototype system that supports hyperparameter search and analysis via interactive visual analytics.

Related publications:
Data-Centric Security
href="https://www.informatica.com/">Informatica
Security Analytics Dashboard:
Video Demo:

The growing number of attacks on sensitive information stored in company databases has required the need for more advanced data protection systems. A new class of data-centric systems is allowing data security teams in organizations to better detect security risks across distributed data stores. However, data security analysts still face two key challenges when making data protection decisions: information overload from too many protection targets and having to build optimal protection plans given current goals and available resources. In this work, we characterize user classes and requirements in data security teams, and propose a system design that separates the decision-making process into two sub-tasks: identifying what data is worth protecting and building an impactful plan to protect it. We implemented a system prototype through four iterative design and evaluation cycles, by applying user-centered design to this new domain of data security applications.

Related publications: