Language model optimization for mental health question answering application

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AN3XP9CJQ" target="_blank" >RIV/00216208:11320/26:N3XP9CJQ - isvavai.cz</a>

Result on the web

<a href="https://ijece.iaescore.com/index.php/IJECE/article/view/37530" target="_blank" >https://ijece.iaescore.com/index.php/IJECE/article/view/37530</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.11591/ijece.v15i5.pp4829-4836" target="_blank" >10.11591/ijece.v15i5.pp4829-4836</a>

Result language

angličtina

Original language name

Language model optimization for mental health question answering application

Original language description

Question answering (QA) is a task in natural language processing (NLP) where the bidirectional encoder representations from transformers (BERT) language model has shown remarkable results. This research focuses on optimizing the IndoBERT and MBERT models for the QA task in the mental health domain, using a translated version of the Amod/mental_health_counseling_conversations dataset on Hugging Face. The optimization process involves fine-tuning IndoBERT and MBERT to enhance their performance, evaluated using BERTScore components: F1, recall, and precision. The results indicate that fine-tuning significantly boosts IndoBERT’s performance, achieving an F1-BERTScore of 91.8%, a recall of 89.9%, and precision of 93.9%, marking a 28% improvement. For the model, M-BERT’s fine-tuning results include an F1-BERTScore of 79.2%, recall of 73.4%, and precision of 86.2%, with only a 5% improvement. These findings underscore the importance of fine-tuning and using language-specific models like IndoBERT for specialized NLP tasks, demonstrating the potential to create more accurate and contextually relevant question-answering systems in the mental health domain.

Czech name

—

Czech description

—

Type

J_ost - Miscellaneous article in a specialist periodical

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

International Journal of Electrical and Computer Engineering (IJECE)

ISSN

2722-2578

e-ISSN

2088-8708

Volume of the periodical

15

Issue of the periodical within the volume

5

Country of publishing house

US - UNITED STATES

Number of pages

8

Pages from-to

4829-4836

UT code for WoS article

—

EID of the result in the Scopus database

—