Classification of Questionnaires with Open-Ended Questions

Miraç Tuğcu, Tolga Çekiç, Begüm Erdinç, Seher Akay, Onur Deniz

2023

Abstract

Questionnaires with open-ended questions are used across industries to collect insights from respondents. The answers to these questions may lead to labelling errors because of the complex questions. However, to handle this noise in the data, manual labour might not be feasible due to low-resource scenarios. Here, we propose an end-to-end solution to handle questionnaire-style data as a text classification problem. In order to mitigate labelling errors, we use a data-centric approach to group inconsistent examples from the banking customer questionnaire dataset in Turkish. For the model architecture, BiLSTM is preferred to capture longterm dependencies between contextualized word embeddings of BERT. We achieved significant results on the binary questionnaire classification task. We obtained results up to 81.9% recall and 79.8% F1 score with the clustering method to clean the dataset and presented the results of how it impacts overall model performance on both the original and clean versions of the data.

Paper Citation

in Harvard Style

Tuğcu M., Çekiç T., Erdinç B., Akay S. and Deniz O. (2023). Classification of Questionnaires with Open-Ended Questions. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-671-2, SciTePress, pages 413-420. DOI: 10.5220/0012233200003598

in Bibtex Style

@conference{kdir23,
author={Miraç Tuğcu and Tolga Çekiç and Begüm Erdinç and Seher Akay and Onur Deniz},
title={Classification of Questionnaires with Open-Ended Questions},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2023},
pages={413-420},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012233200003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Classification of Questionnaires with Open-Ended Questions
SN - 978-989-758-671-2
AU - Tuğcu M.
AU - Çekiç T.
AU - Erdinç B.
AU - Akay S.
AU - Deniz O.
PY - 2023
SP - 413
EP - 420
DO - 10.5220/0012233200003598
PB - SciTePress