GPT is an effective tool for multilingual psychological text analysis

S Rathje, DM Mirea, I Sucholutsky, R Marjieh… - Proceedings of the …, 2024 - pnas.org
The social and behavioral sciences have been increasingly using automated text analysis to
measure psychological constructs in text. We explore whether GPT, the large-language …

Afrisenti: A twitter sentiment analysis benchmark for african languages

SH Muhammad, I Abdulmumin, AA Ayele… - arxiv preprint arxiv …, 2023 - arxiv.org
Africa is home to over 2,000 languages from more than six language families and has the
highest linguistic diversity among all continents. These include 75 languages with at least …

Bactrian-x: Multilingual replicable instruction-following models with low-rank adaptation

H Li, F Koto, M Wu, AF Aji, T Baldwin - arxiv preprint arxiv:2305.15011, 2023 - arxiv.org
Instruction tuning has shown great promise in improving the performance of large language
models. However, research on multilingual instruction tuning has been limited due to the …

MaChAmp at SemEval-2023 tasks 2, 3, 4, 5, 7, 8, 9, 10, 11, and 12: On the Effectiveness of Intermediate Training on an Uncurated Collection of Datasets.

R Van Der Goot - Proceedings of the 17th International Workshop …, 2023 - aclanthology.org
To improve the ability of language models to handle Natural Language Processing (NLP)
tasks and intermediate step of pre-training has recently beenintroduced. In this setup, one …

Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences

C Suhaeni, HS Yong - Applied Sciences, 2023 - mdpi.com
In this paper, we explore the effectiveness of the GPT-3 model in tackling imbalanced
sentiment analysis, focusing on the Coursera online course review dataset that exhibits high …

Robustness of models addressing Information Disorder: A comprehensive review and benchmarking study

G Fenza, V Loia, C Stanzione, M Di Gisi - Neurocomputing, 2024 - Elsevier
Abstract Machine learning and deep learning models are increasingly susceptible to
adversarial attacks, particularly in critical areas like cybersecurity and Information Disorder …

Nlnde at semeval-2023 task 12: Adaptive pretraining and source language selection for low-resource multilingual sentiment analysis

M Wang, H Adel, L Lange, J Strötgen… - arxiv preprint arxiv …, 2023 - arxiv.org
This paper describes our system developed for the SemEval-2023 Task 12" Sentiment
Analysis for Low-resource African Languages using Twitter Dataset". Sentiment analysis is …

The skipped beat: A study of sociopragmatic understanding in llms for 64 languages

C Zhang, KD Doan, Q Liao… - arxiv preprint arxiv …, 2023 - arxiv.org
Instruction tuned large language models (LLMs), such as ChatGPT, demonstrate remarkable
performance in a wide range of tasks. Despite numerous recent studies that examine the …

Evaluating emotion arcs across languages: Bridging the global divide in sentiment analysis

D Teodorescu, SM Mohammad - arxiv preprint arxiv:2306.02213, 2023 - arxiv.org
Emotion arcs capture how an individual (or a population) feels over time. They are widely
used in industry and research; however, there is little work on evaluating the automatically …

UMUTeam at SemEval-2023 task 12: Ensemble learning of LLMs applied to sentiment analysis for low-resource African languages

JA García-Díaz, C Caparros-Laiz… - Proceedings of the …, 2023 - aclanthology.org
These working notes summarize the participation of the UMUTeam in the SemEval 2023
shared task: AfriSenti, focused on Sentiment Analysis in several African languages. Two …