

AI Chatbot for Research
Designed keyword refinement feature for an AI-powered literature search tool during the summer internship at Transformative Learning Technologies Lab.
Type
Web design
AI search design
Time
12 weeks
(2023 Summer)
Team
Yolanda | UX designer team A
Peiying | UX designer, team A
Dora | UX designer, team B
Sabrina | UX designer, team B
Yipu Zheng | lead & engineer
Skills
Design sprint
AI interaction design
Visual guide
UI kit

“I don't even know the keywords to find the papers I need!”
Success Metrics
1. Measure the reduction in the time it takes for researchers to find relevant papers compared to traditional methods
2. Collect feedback from users to gauge their satisfaction on a scale of 5 with the tool's effectiveness
Design Goal
Guide novices in using AI to make finding research papers easier and faster
My Responsibilities
🖌️ Need-finding through research and competitors' audit
🏠 Build visual guide and UI kit following Material Design
🤖️ Design interactions with AI chatbot
Background
In March 2023, a paper from Transformative Learning Technologies Lab (pioneered in AI-powered learning tools design)—“Outside-in, Inside-out, or Outside-out? Exploring the Flow of New Ideas and the Development of CSCL and ICLS via Co-Authorship Networks from 1995 to 2020” conducted keyword analysis and social network analysis of all the papers in Learning Science from 1995 to 2020.
There are altogether 5,091 papers, and 8,225 authors.
Thus was born a huge database and we want to design something from it.

Overview
Problem Statement
Final Design
ROUND #1 SELECT
Here are the keywords you can definitely use!
Use academic terms over self-created ones for precision.
-
Instant Feedback: Clicking on the keywords refreshes the results on the right automatically without second clicking
-
Categorized Keywords: keywords are grouped by categories, content, methodology, interdisciplinary, etc.
-
Selection Recap: users can find what keywords they have selected and been extracted to generate the results


ROUND #2 REGENERATE
Don't worry;
you can try again.
It is normal that a one-time search is not enough.
-
Regenerate Button: click the "Regenerate" button to let AILit refresh itself and do the search again
-
Search History: you can find first-round keywords in the history by clicking on the pagination
ROUND #3 EDIT KEYWORDS
Still unwanted results? Edit them on your own!
AILit allows manual editing to happen more seamlessly.
-
Edit and Save: users can manually replace selected keywords with other edited keywords
-
Sync and Search: the newly edited keywords are synced on the reminder on the chatbot automatically
