A deep insight in chat analysis: collaboration, evolution and evaluation, summarization and search

  • Authors:
  • Mihai Dascalu;Traian Rebedea;Stefan Trausan-Matu

  • Affiliations:
  • University "Politehnica" of Bucharest, Bucharest, Romania and S.C. CCT S.R.L., Bucharest, Romania;University "Politehnica" of Bucharest, Bucharest, Romania;University "Politehnica" of Bucharest, Bucharest, Romania and Romanian Academy Research Institute for Artificial Intelligence, Bucharest, Romania

  • Venue:
  • AIMSA'10 Proceedings of the 14th international conference on Artificial intelligence: methodology, systems, and applications
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Chat-like conversations are very popular and are often used by members of communities of practice to share ideas, propose solutions and to solve problems. With the advent and increasing popularity of Computer Supported Collaborative Learning (CSCL), chat conversations have also started to be used in a formal educational setting. However, the main problem when tutors tried to assess their students' chat conversations is that this process is very difficult and time consuming. Therefore, several efforts have been undertaken during the last years to develop a tool that supports the analysis of collaborative chat conversations used in an educational context. In this paper, we propose a solution based on Natural Language Processing (NLP), Social Network Analysis (SNA) and Latent Semantic Analysis (LSA) that can be used for several tasks: assessment of utterances and participants, important topics visualization, summarization and semantic search. Furthermore, a summary with the key findings from the first validation round of using this approach is presented.