Deploy automated analysis tools to support tutors' time-consuming analysis of CSCL conversations¶

Strategy · All strategies
Evidence · 1 claim (1 for) · 1 study (1 design), q1 · 0 of 1 report an effect size · 1 claim rests on one study

Description¶

The article recommends automated collaboration-assessment tools because, as CSCL gains broader usage, analyzing chat conversations manually burdens tutors. It aims to support "tutors in the time-consuming process of analyzing conversations" by applying the two ReaderBench models to collaboration assessment, so evaluation of collaboration need not rest entirely on human reading of chats.

Design Implications¶

Context¶

Requirements¶

• Suitable for CSCL settings where tutors must analyze participant conversations.

Constraints¶

Target Learners¶

• Tutors analyzing CSCL conversations

Target Learning Goals¶

• Timely assessment and feedback on collaboration in CSCL

Claims¶

• Two computational models were proposed and validated for assessing collaboration in CSCL conversations [+W]

Related Strategies¶

• Use automated collaboration assessments as scaffolds for reflection rather than ground truth
• Use automatic reflection classification for preliminary feedback and workload support, with final assessment retained by educators

Examples¶

-

Key Sources¶

• Mihai Dascalu, Stefan Trausan-Matu, Danielle S. Mcnamara, Philippe Dessus. (2015). ReaderBench – Automated Evaluation of Collaboration based on Cohesion and Dialogism. International Journal of Computer-Supported Collaborative Learning. https://doi.org/10.1007/s11412-015-9226-y