INSURANCE DOMAIN QUESTION-ANSWERING DIGITAL ASSISTANT

Authors

  • Стефан Драгичевић Autor
  • Јелена Сливка Autor

DOI:

https://doi.org/10.24867/32BE19Dragicevic

Keywords:

NLP, chatbot, LSTM, sentiment classification

Abstract

This paper presents the development of an advanced chatbot system designed to answer insurancerelated questions automatically. The system is implemented as a web application that provides users with quick and clear answers to their questions. The system consists of several key modules: a query preprocessing module, a model for finding relevant questions (high recall), a model for filtering and selecting the most relevant answer (high precision), a sentiment classification module, and a keyword extraction module.

References

[1] Adamopoulou & Moussiades (2020). An Overview of Chatbot Technology. AIAI 2020, IFIP Advances, 584. Springer.

[2] Jatnikaa et al. (2019). Word2VecModel Analysis for Semantic Similarities. ICCSCI 2019.

[3] Lv et al. Siamese Multiplicative LSTM for Semantic Text Similarity.

[4] Devika et al. Sentiment Analysis: A Comparative Study On Different Approaches. ICRTCSE.

[5] Bonta et al. (2019). A Comprehensive Study on Lexicon-Based Approaches. Asian J Comp Sci Tech, 8(S2).

[6] Xu & Zhang (2020). Extracting Keywords from Texts. ICIIK.

[7] https://paperswithcode.com/sota/question-answeringon-quora-question-pairs

[8] https://huggingface.co/datasets/quoracompetitions/quora

[9] https://www.kaggle.com/datasets/lakshmi25npathi/imdbdataset-of-50k-movie-reviews

[10] https://github.com/shuzi/insuranceQA

Published

2025-10-27

Issue

Section

Electrotechnical and Computer Engineering