Each semester every Penn State student must to select courses for next semester. Too many students ask the same common questions to academic advisor every semester, “What class should I take next semester”, “What do you recommend that I take next semester” “What course do I need for my major”, etc. The courses search process needs to be improved in order to save time and resources for students and advisors. Therefore, we decided to build a chatbot that supports this process.
What it does
This chatbot helps students for searching courses for next semester. Chatbot takes inputs from students about what classes they already take (preliminary data). Once that is done, students can interact with Watson Conversation to get the best advice for next semester classes.
What we have finished
A functional chatbot that can recommend classes to you based on your major and your semester standing, as well as your interest. Due to the nature of AI, since it is new, we only have 2 available majors: Computer Science and Mathematic, and only a few classes.
The chatbot also come with 2 search functions for professors and classes search, utilizing Google Search API and PSU Directory search API.
How We built it
To build this application, we utilized a demo provided by IBM to get the core chatbot set up and then modified it. We also built a website for Mr. Watson, although because of the time constraint we haven’t been able to integrate the website into part of the demo. We also embed extra data onto the payload send back and forth by Watson Conversation API so that we can integrate it with Google API and PSU Directory API.
Challenges We ran into
One of the biggest challenge we ran into programming-wise was that the Watson IBM Conversation had a very specific setup to it. Jacqueline couldn’t figure out how to have the client show the Google API and Directory API as a chatbot data, and she spent a good amount of time trying various test case. Another problem we ran into was the size of the team, we started out with 5 people, but after just about 5 hours 2 lefts and we had more work to do.
Accomplishments that We are proud of
We are proud that we were able to integrate IBM Watson Conversation to work with the Penn State Directory to pull information of the professor that we searched.
What I learned
What's next for Mr. Watson Student Advisor
Expanding its knowledge library to work with more courses and majors.