UMass Dartmouth Blue Economy LLM: Unifying Platform for Southcoast Massachusetts for Blue Economy Using AI and LLM (Unofficial, In Progress)

Blue Economy is fundamental to Southcoast Massachusetts for its history, with New Bedford serving as the nation’s highest-value fishing port. Our region faces emerging challenges from technological change, globalization, and post-pandemic recovery that affect our coastal communities.

This project develops an innovative AI and Large Language Models to help address these challenges by:

  • Connecting communities with information and opportunities
  • Supporting local business development
  • Enhancing regional competitiveness
  • Improving access to jobs and career paths
  • Creating hands-on AI experience for students
  • Building professional networks in the blue economy

Recent Progresses in AI

  • In March 2016, AlphaGo beat Lee Sedol in the game of GO. (Documentary)
  • In December 2024, OpenAI o3 has scored a breakthrough 75.7% on the Semi-Private Evaluation set at our stated public leaderboard $10k compute limit. A high-compute (172x) o3 configuration scored 87.5%. (François Chollet’s Blog)

Use Cases in Businesses.

Use Cases in the Universities.

Case Study in Georgia State University.

“Georgia State’s pioneering, artificial intelligence-enhanced chatbot “Pounce” is well established as an institutional tool for helping incoming students navigate the thorny world of finances, registration and just getting started in college. Now, Georgia State is showing student performance jumps when classes employ the chatbot to keep them connected.

Receiving direct text messages about their class assignments, academic supports and course content increased the likelihood students would earn a B or higher and, for first-generation students, increased their likelihood of passing the class. First-generation students receiving the messages earned final grades about 11 points higher than their peers.

‘Eleven points is more than a full letter grade, and a full letter grade can be the difference between students holding onto their HOPE Scholarship and Pell Grant awards or not,” said Timothy M. Renick, the founding executive director of the National Institute for Student Success at Georgia State. ‘These are exceptional results from a fairly light-touch initiative.’“(“Classroom Chatbot Improves Student Performance, Study Says“)

Academic Research on the Effectiveness of Chatbot by Researchers at Brown University, Brookings, Georgia Institute of Technology, Georgia State University, Johns Hopkins University, and UT Austin.

“Through two experimental studies, we assessed the effectiveness of an artificially
intelligent text-based chatbot that provided proactive outreach and support to college students to
navigate administrative processes and use campus resources. In both the two-year and four-year
college context, outreach was most effective when focused on discrete administrative processes
such as filing financial aid forms or registering for courses which were acute, time-sensitive, and
for which outreach could be targeted to those for whom it was relevant.”

(Page, L.C., K. Meyer, J. Lee, et al. 2023. “Conditions Under Which College Students Can Be Responsive to Nudging.”)

“This study reports on the causal effects of using a non-generative artificial intelligence (AI) chatbot to provide
course-specific, proactive outreach and support to students in large-enrollment undergraduate courses. Across
both an American Government and Microeconomics course, students randomly assigned to receive chatbot
messaging were four percentage points more likely to earn an A or B in the courses.”

(Meyer, K, L.C. Page, C. Mata, et al. 2024. “Let’s Chat: Leveraging Chatbot Outreach for Improved Course Performance.”)

Use Cases in Governments

The platform proposes to process information from:

  • University of Massachusetts Dartmouth
  • Woods Hole Oceanographic Institution (WHOI)
  • New England Fishery Management Council (NEFMC)
  • City of New Bedford
  • Town of Dartmouth
  • Town of Westport
  • Southcoast Health

This is a collaborative effort between:

  • Division of Student Affairs
  • College of Arts and Sciences
  • Charlton College of Business
  • College of Engineering

Future development:

  • Internship and job opportunities
  • Sustainable business resources
  • Healthcare access information

This is a research prototype demonstrating the potential of AI and large language models to serve our coastal communities. As an experimental system, outputs should be verified before use in practical applications.

We thank the students, faculty, and staff who have contributed to this ongoing research initiative.

Update on 12/25/2024. During the winter break, we focused on the following pages with improved responoses. The current version will answer questions from these pages. Please note that the current version will not reliably answer questions about topics not covered in the pages listed below. (Expanding coverage will be a future step.)

We developed the first version in May 2024. The July 2024 version included data from UMass Dartmouth, WHOI, City of New Bedford, Town of Dartmouth, Town of Westport, and Southcoast Health. Due to current resource limitations as we teach classes, the current system has very limited capabilities. The chatbot interface is currently in reconstruction. In the long-run, we plan to implement novel algorithms to reduce hallucinations and improve response accuracy compared with current large language models, building on research described in Kazumori (2024).