A data-driven approach for the identification of features for automated feedback on academic essays
For predicting and improving the quality of essays, text analytic metrics (surface, syntactic, morphological, and semantic features) can be used to provide formative feedback to the students in higher education. In this study, the goal was to identify a sufficient number of features that exhibit a f...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
29 September 2023
|
| In: |
IEEE transactions on learning technologies
Year: 2023, Jahrgang: 16, Heft: 6, Pages: 914-925 |
| ISSN: | 1939-1382 |
| DOI: | 10.1109/TLT.2023.3320877 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1109/TLT.2023.3320877 Verlag, lizenzpflichtig, Volltext: https://ieeexplore.ieee.org/document/10268328 |
| Verfasserangaben: | Mohsin Abbas, Peter van Rosmalen, Marco Kalz |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1895999537 | ||
| 003 | DE-627 | ||
| 005 | 20241205153553.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240722s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TLT.2023.3320877 |2 doi | |
| 035 | |a (DE-627)1895999537 | ||
| 035 | |a (DE-599)KXP1895999537 | ||
| 035 | |a (OCoLC)1475303435 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 02 |2 sdnb | ||
| 100 | 1 | |a Abbas, Mohsin |e VerfasserIn |0 (DE-588)1336466332 |0 (DE-627)1896001009 |4 aut | |
| 245 | 1 | 2 | |a A data-driven approach for the identification of features for automated feedback on academic essays |c Mohsin Abbas, Peter van Rosmalen, Marco Kalz |
| 264 | 1 | |c 29 September 2023 | |
| 300 | |a 12 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 22.07.2024 | ||
| 520 | |a For predicting and improving the quality of essays, text analytic metrics (surface, syntactic, morphological, and semantic features) can be used to provide formative feedback to the students in higher education. In this study, the goal was to identify a sufficient number of features that exhibit a fair proxy of the scores given by the human raters via a data-driven approach. Using an existing corpus and a text analysis tool for the Dutch language, a large number of features were extracted. Artificial neural networks, Levenberg-Marquardt algorithm, and backward elimination were used to reduce the number of features automatically. Irrelevant features were eliminated based on the inter-rater agreement between predicted and human scores calculated using Cohen's kappa (κ). The number of features in this study was reduced from 457 to 28 and grouped into different categories. The results reported in this article are an improvement over a similar previous study. First, the inter-rater reliability between the predicted scores and human raters was increased by tweaking the corpus for overfitting for average scores. The resulting maximum value of κ showed substantial agreement compared to moderate inter-rater reliability in the prior study. Second, instead of using a dedicated training and test set, the training and testing phases in the new experiments were performed using k-fold cross validation on the corpus of texts. The approach presented in this research article is the first step toward our ultimate goal of providing meaningful formative feedback to the students for enhancing their writing skills and capabilities. | ||
| 650 | 4 | |a Artificial neural networks | |
| 650 | 4 | |a backward elimination | |
| 650 | 4 | |a dimensionality reduction | |
| 650 | 4 | |a Feature extraction | |
| 650 | 4 | |a feature reduction | |
| 650 | 4 | |a feature selection | |
| 650 | 4 | |a k -fold cross validation | |
| 650 | 4 | |a Levenberg-Marquardt (LM) | |
| 650 | 4 | |a Measurement | |
| 650 | 4 | |a natural language processing | |
| 650 | 4 | |a Semantics | |
| 650 | 4 | |a Surface morphology | |
| 650 | 4 | |a Syntactics | |
| 650 | 4 | |a Training | |
| 650 | 4 | |a Writing | |
| 700 | 1 | |a Van Rosmalen, Peter |e VerfasserIn |0 (DE-627)1581954913 |0 (DE-576)511954913 |4 aut | |
| 700 | 1 | |a Kalz, Marco |e VerfasserIn |0 (DE-588)1196743355 |0 (DE-627)1678608629 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |a Institute of Electrical and Electronics Engineers |t IEEE transactions on learning technologies |d New York, NY : IEEE, 2008 |g 16(2023), 6, Seite 914-925 |h Online-Ressource |w (DE-627)581030567 |w (DE-600)2454421-8 |w (DE-576)286687399 |x 1939-1382 |7 nnas |
| 773 | 1 | 8 | |g volume:16 |g year:2023 |g number:6 |g pages:914-925 |g extent:12 |a A data-driven approach for the identification of features for automated feedback on academic essays |
| 856 | 4 | 0 | |u https://doi.org/10.1109/TLT.2023.3320877 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u https://ieeexplore.ieee.org/document/10268328 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20240722 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 1196743355 |a Kalz, Marco |m 1196743355:Kalz, Marco |p 3 |y j | ||
| 999 | |a KXP-PPN1895999537 |e 4555426126 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"language":["eng"],"recId":"1895999537","note":["Gesehen am 22.07.2024"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"person":[{"family":"Abbas","given":"Mohsin","roleDisplay":"VerfasserIn","display":"Abbas, Mohsin","role":"aut"},{"family":"Van Rosmalen","given":"Peter","display":"Van Rosmalen, Peter","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Marco","family":"Kalz","role":"aut","roleDisplay":"VerfasserIn","display":"Kalz, Marco"}],"title":[{"title_sort":"data-driven approach for the identification of features for automated feedback on academic essays","title":"A data-driven approach for the identification of features for automated feedback on academic essays"}],"relHost":[{"note":["Gesehen am 07.03.19","Fortsetzung der CD-ROM-Ausgabe"],"disp":"Institute of Electrical and Electronics EngineersIEEE transactions on learning technologies","type":{"media":"Online-Ressource","bibl":"periodical"},"recId":"581030567","language":["eng"],"corporate":[{"role":"aut","roleDisplay":"VerfasserIn","display":"Institute of Electrical and Electronics Engineers"}],"pubHistory":["1.2008 -"],"titleAlt":[{"title":"Learning technologies"},{"title":"Transactions on learning technologies"}],"part":{"year":"2023","issue":"6","pages":"914-925","volume":"16","text":"16(2023), 6, Seite 914-925","extent":"12"},"title":[{"title":"IEEE transactions on learning technologies","title_sort":"IEEE transactions on learning technologies"}],"physDesc":[{"extent":"Online-Ressource"}],"origin":[{"publisherPlace":"New York, NY","dateIssuedDisp":"2008-","dateIssuedKey":"2008","publisher":"IEEE"}],"id":{"zdb":["2454421-8"],"eki":["581030567"],"issn":["1939-1382"]}}],"physDesc":[{"extent":"12 S."}],"name":{"displayForm":["Mohsin Abbas, Peter van Rosmalen, Marco Kalz"]},"id":{"eki":["1895999537"],"doi":["10.1109/TLT.2023.3320877"]},"origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"29 September 2023"}]} | ||
| SRT | |a ABBASMOHSIDATADRIVEN2920 | ||