A comparative study of cross-lingual sentiment analysis

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43971423" target="_blank" >RIV/49777513:23520/24:43971423 - isvavai.cz</a>

Result on the web

<a href="https://www.sciencedirect.com/science/article/pii/S095741742400112X" target="_blank" >https://www.sciencedirect.com/science/article/pii/S095741742400112X</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.eswa.2024.123247" target="_blank" >10.1016/j.eswa.2024.123247</a>

Result language

angličtina

Original language name

A comparative study of cross-lingual sentiment analysis

Original language description

This paper presents a detailed comparative study of the zero-shot cross-lingual sentiment analysis. Namely, we use modern multilingual Transformer-based models and linear transformations combined with CNN and LSTM neural networks. We evaluate their performance in Czech, French, and English. We aim to compare and assess the models’ ability to transfer knowledge across languages and discuss the trade-off between their performance and training/inference speed. We build strong monolingual baselines comparable with the current SotA approaches, achieving state-of-the-art results in Czech (96.0% accuracy) and French (97.6% accuracy). Next, we compare our results with the latest large language models (LLMs), i.e., Llama 2 and ChatGPT. We show that the large multilingual Transformer-based XLM-R model consistently outperforms all other cross-lingual approaches in zero-shot cross-lingual sentiment classification, surpassing them by at least 3%. Next, we show that the smaller Transformer-based models are comparable in performance to older but much faster methods with linear transformations. The best-performing model with linear transformation achieved an accuracy of 92.1% on the French dataset, compared to 90.3% received by the smaller XLM-R model. Notably, this performance is achieved with just approximately 0.01 of the training time required for the XLM-R model. It underscores the potential of linear transformations as a pragmatic alternative to resource-intensive and slower Transformer-based models in real-world applications. The LLMs achieved impressive results that are on par or better, at least by 1%–3%, but with additional hardware requirements and limitations. Overall, this study contributes to understanding cross-lingual sentiment analysis and provides valuable insights into the strengths and limitations of cross-lingual approaches for sentiment analysis

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

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

S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

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

Name of the periodical

Expert Systems with Applications

ISSN

0957-4174

e-ISSN

1873-6793

Volume of the periodical

247

Issue of the periodical within the volume

AUG 1 2024

Country of publishing house

NL - THE KINGDOM OF THE NETHERLANDS

Number of pages

39

Pages from-to

—

UT code for WoS article

001171252000001

EID of the result in the Scopus database

2-s2.0-85185192813