Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hasan, Md. Arid, Das, Shudipta, Anjum, Afiyat, Alam, Firoj, Anjum, Anika, Sarker, Avijit, Noori, Sheak Rashed Haider
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914741553725440
author Hasan, Md. Arid
Das, Shudipta
Anjum, Afiyat
Alam, Firoj
Anjum, Anika
Sarker, Avijit
Noori, Sheak Rashed Haider
author_facet Hasan, Md. Arid
Das, Shudipta
Anjum, Afiyat
Alam, Firoj
Anjum, Anika
Sarker, Avijit
Noori, Sheak Rashed Haider
contents The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.
format Preprint
id arxiv_https___arxiv_org_abs_2308_10783
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis
Hasan, Md. Arid
Das, Shudipta
Anjum, Afiyat
Alam, Firoj
Anjum, Anika
Sarker, Avijit
Noori, Sheak Rashed Haider
Computation and Language
Machine Learning
68T50
I.2.7
The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.
title Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis
topic Computation and Language
Machine Learning
68T50
I.2.7
url https://arxiv.org/abs/2308.10783