Artificial intelligence and machine learning in Islamic banking: insights using lexicon and machine learning-based models

Purpose This study aims to investigate the integration of artificial intelligence (AI) and machine learning (ML) within the Islamic banking sector, focusing on sentiment analysis of these technologies across annual reports from 71 full-fledged Islamic banks in 16 countries between 2015 and 2023. Design/methodology/approach The authors used five sentiment analysis models, TextBlob, valence aware dictionary and sentiment reasoner, AFINN, long short-term memory (LSTM) and bidirectional encoder representations from transformers (BERT), to assess sentiment polarity and word frequency of AI and ML terms using Python. Sentiment distributions and trends were analysed across time, country and individual banks using visualisations from R Studio. Findings The results indicate a predominantly positive sentiment towards AI and ML in Islamic banking, with advanced models like LSTM and BERT capturing nuanced sentiment more accurately than traditional models. Regional differences emerged, with countries like Saudi Arabia, Qatar and the UAE demonstrating notably higher positive sentiment levels. The findings reveal significant sentiment variations among models, countries and banks, emphasising AI and ML’s perceived value in enhancing efficiency, compliance and customer experience. Research limitations/implications The study’s reliance on annual reports may limit sentiment scope, suggesting future research could expand to other data sources for a comprehensive view. Practical implications The findings offer valuable insights for Islamic banks, regulators and stakeholders to inform responsible AI adoption and its application in enhancing service quality and regulatory compliance. Originality/value This research fills a notable gap by examining AI and ML sentiment in Islamic finance, providing new insights into stakeholder perspectives on these technologies’ role and impact.

Authors

Institutions

Publication Details

Journal
Journal of Islamic marketing
Published
2026-11-20
DOI
https://doi.org/10.1108/jima-03-2025-0162
Primary Topic
Sentiment Analysis and Opinion Mining
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial intelligence and machine learning in Islamic banking: insights using lexicon and machine learning-based models

Hassnian Ali, Ahmet Faruk Aysan, Syed Zain Ul Hassan Bukhari
4 links
Journal of Islamic marketing
Sentiment Analysis and Opinion Mining
article

Artificial intelligence and machine learning in Islamic banking: insights using lexicon and machine learning-based models

Hassnian Ali, Ahmet Faruk Aysan, Syed Zain Ul Hassan Bukhari
article en

Abstract

Purpose This study aims to investigate the integration of artificial intelligence (AI) and machine learning (ML) within the Islamic banking sector, focusing on sentiment analysis of these technologies across annual reports from 71 full-fledged Islamic banks in 16 countries between 2015 and 2023. Design/methodology/approach The authors used five sentiment analysis models, TextBlob, valence aware dictionary and sentiment reasoner, AFINN, long short-term memory (LSTM) and bidirectional encoder representations from transformers (BERT), to assess sentiment polarity and word frequency of AI and ML terms using Python. Sentiment distributions and trends were analysed across time, country and individual banks using visualisations from R Studio. Findings The results indicate a predominantly positive sentiment towards AI and ML in Islamic banking, with advanced models like LSTM and BERT capturing nuanced sentiment more accurately than traditional models. Regional differences emerged, with countries like Saudi Arabia, Qatar and the UAE demonstrating notably higher positive sentiment levels. The findings reveal significant sentiment variations among models, countries and banks, emphasising AI and ML’s perceived value in enhancing efficiency, compliance and customer experience. Research limitations/implications The study’s reliance on annual reports may limit sentiment scope, suggesting future research could expand to other data sources for a comprehensive view. Practical implications The findings offer valuable insights for Islamic banks, regulators and stakeholders to inform responsible AI adoption and its application in enhancing service quality and regulatory compliance. Originality/value This research fills a notable gap by examining AI and ML sentiment in Islamic finance, providing new insights into stakeholder perspectives on these technologies’ role and impact.

Journal of Islamic marketing
Minhaj University Lahore (PK), Hamad bin Khalifa University (QA)
Sentiment Analysis and Opinion Mining
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon