CoChat

Enhancing argumentative writing with automated feedback and social comparison nudging

Open access
Wambsganss, Thiemo, Janson, Andreas, Leimeister, Jan Marco · 2022 · Computers & Education
Cited by 71

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Abstract

The advantages offered by natural language processing (NLP) and machine learning enable students to receive automated feedback on their argumentation skills, independent of educator, time, and location. Although there is a growing amount of literature on formative argumentation feedback, empirical evidence on the effects of adaptive feedback mechanisms and novel NLP approaches to enhance argumentative writing remains scarce. To help fill this gap, the aim of the present study is to investigate whether automated feedback and social comparison nudging enable students to internalize and improve logical argumentation writing abilities in an undergraduate business course. We conducted a mixed-methods study to investigate the impact of argumentative writing on 71 students in a field experiment. Students in treatment group 1 completed their assignment while receiving automated feedback, whereas students in treatment group 2 completed the same assignment while receiving automated feedback with a social comparison nudge that indicated how other students performed on the same assignment. Students in the control group received generalized feedback based on rules of syntax. We found that participants who received automated argumentation feedback with a social comparison nudge wrote more convincing texts with higher-quality argumentation compared to the two benchmark groups (p < 0.05). The measured self-efficacy, perceived ease of use, and qualitative data provide valuable insights that help explain this effect. The results suggest that embedding automated feedback in combination with social comparison nudges enables students to increase their argumentative writing skills by triggering psychological processes. Receiving only automated feedback in the form of in-text argumentative highlighting without any further guidance appears not to significantly influence students’ writing abilities when compared to syntactic feedback.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.compedu.2022.104644

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 71

Metadata

Authors
Wambsganss, T., Janson, A., & Leimeister, J. M.
Venue
Computers & Education
Publisher
Elsevier BV
Published
2022-12
Volume
191
Pages
104644
ISSN
0360-1315 (ISSN-L)
OpenAlex
W4300716842
Cited by
71
References
19
FWCI
27.52
Type
journal article
Language
en
Open access
hybrid

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.