Multiple Episode Protocol Analysis (MEPA)

Product or Programme · All products and programmes
Evidence · 3 claims (2 for, 1 mixed) · 2 studies (1 associational, 1 design), q2–q3 · 0 of 2 report an effect size · 3 claims rest on one study

Description

A computer program developed by Erkens et al. that uses production rules to automatically segment chat messages and code dialogue acts in collaborative-learning protocols.

Components

• MEPA production rule system for automatic dialogue act coding: The Multiple Episode Protocol Analysis (MEPA) computer program hosts a production rule system that automatically categorizes utterances into dialogue acts. "A set of if-then rules uses pattern matching to look for typical words or phrases, in this case for discourse markers or clue phrases." It comprises "a rule system for automatic segmentation of combined utterances in single messages (300 rules) and a rule system for dialogue act coding (1,250 rules)", and "MEPA is able to code a protocol consisting of 1,000 utterances in less than a second." A segmentation filter splits chat contributions on punctuation, connectives, and starting discourse markers, with exception rules preventing erroneous splits. (Erkens et al. (2008))
• Analyze writing process data temporally, taking the moments at which cognitive activities occur into account: The article advocates analyzing cognitive processing during writing as a function of the moment in task execution, for example by splitting protocols into equally long episodes and modelling activity occurrence per episode. As the authors put it, "analyses of cognitive processing during writing should take the moment(s) at which cognitive activities occur into account." In this study this temporal modelling is what allowed offline questionnaire scores to predict online behaviour at all. (Tillema et al. (2011))

Claims

• Automatic DAC coding of dialogue acts agrees substantially with manual coding (79.0% agreement, kappa 0.75) [+M]
• The occurrence of six (meta)cognitive writing activities varies significantly across episodes of task execution [+M]
• Planner and reviser questionnaire scores show frequency main effects on several online activities, with no interaction with episode [~M]

Related Products and Programmes

-

Key Sources

• Erkens, G., & Janssen, J. (2008). Automatic coding of dialogue acts in collaboration protocols. Computer-Supported Collaborative Learning, 3, 447-470. https://doi.org/10.1007/s11412-008-9052-6
• Tillema, M., van den Bergh, H., Rijlaarsdam, G., & Sanders, T. (2011). Relating self reports of writing behaviour and online task execution using a temporal model. Metacognition and Learning. https://doi.org/10.1007/s11409-011-9072-x

Page metadata

Field	Value
type	product
id	multiple-episode-protocol-analysis-mepa
title	Multiple Episode Protocol Analysis (MEPA)
description	A computer program developed by Erkens et al.
status	review
product_kind	software
generated	by process:settle-candidates on 2026-10-18
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.