Dialogue Act Coding (DAC) system¶
Research Method · All research methods
Evidence · 2 claims (1 for, 1 mixed) · 1 study (1 design),q3· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
The DAC system identifies "dialogue acts", the communicative function of each utterance typed during online collaboration, building on the Verbal Observation System and discourse-analysis research. Its core assumption is that language users "signal the intended meaning and interpretation of their utterances to their discourse partners by means of explicit 'discourse markers'". It distinguishes five main communicative functions: "(1) Argumentative..., (2) Responsive..., (3) Elicitative..., (4) Informative..., and (5) Imperative (commands)", specifying "a total of 29 different dialogue acts". The system was used in CSCL studies of history and language arts inquiry tasks.
Accounts¶
- Dialogue Act Coding (DAC) system: five communicative functions and 29 dialogue acts recognized via discourse markers: The DAC system identifies "dialogue acts", the communicative function of each utterance typed during online collaboration, building on the Verbal Observation System and discourse-analysis research. Its core assumption is that language users "signal the intended meaning and interpretation of their utterances to their discourse partners by means of explicit 'discourse markers'". It distinguishes five main communicative functions: "(1) Argumentative..., (2) Responsive..., (3) Elicitative..., (4) Informative..., and (5) Imperative (commands)", specifying "a total of 29 different dialogue acts". The system was used in CSCL studies of history and language arts inquiry tasks. (Erkens et al. (2008))
- Default catch-all code (InfStm?) flags uncodable messages for manual checking: When the DAC filter finds no discourse marker in a message, it assigns the InfStm? code as a default catch-all, marking the message for manual checking rather than risking a wrong automatic code. The article states "If the system does not find a discourse marker in a message, the message is coded by the label InfStm? as a default catch-all." This means "the researcher still has to check and code some parts of the protocol (about 10%)", but the job is simplified because large parts are already coded and uncoded parts are easy to find.
Claims¶
- Automatic DAC coding of dialogue acts agrees substantially with manual coding (79.0% agreement, kappa 0.75) [+M]
- DAC reliability varies by category: Informatives (especially negative evaluations and nonsense statements) code poorly [~M]
Related Research Methods¶
-
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
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
dialogue-act-coding-dac-system |
title |
Dialogue Act Coding (DAC) system |
description |
The DAC system identifies "dialogue acts", the communicative function of each utterance typed during online collaboration, building on the Verbal Observation System and discourse-analysis research. |
status |
review |
moved_from |
strategy/infstm-catchall-default-code-strategy |
generated |
by process:settle-candidates on 2026-10-18 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — erkens-2008 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.