Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets

被引：5

作者：

Thakkar, Gaurish ^{[1
]}

Pinnis, Marcis ^{[2
,3
]}

机构：

[1] Univ Zagreb, Fac Humanities & Social Sci, Ul Ivana Lucica 3, Zagreb 10000, Croatia

[2] Tilde, Vienibas Gatve 75A, LV-1004 Riga, Latvia

[3] Univ Latvia, Raina Bulv 19-125, LV-1586 Riga, Latvia

来源：

HUMAN LANGUAGE TECHNOLOGIES - THE BALTIC PERSPECTIVE (HLT 2020) | 2020年 / 328卷

关键词：

Sentiment analysis; word embeddings; BERT; Latvian;

D O I：

10.3233/FAIA200602

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present various pre-training strategies that aid in improving the accuracy of the sentiment classification task. At first, we pre-train language representation models using these strategies and then fine-tune them on the downstream task. Experimental results on a time-balanced tweet evaluation set show the improvement over the previous technique. We achieve 76% accuracy for sentiment analysis on Latvian tweets, which is a substantial improvement over previous work.

引用

页码：55 / 61

页数：7

共 50 条

[1] Fine-Tuning of Word Embeddings for Semantic Sentiment Analysis
Atzeni, Mattia
Recupero, Diego Reforgiato
SEMANTIC WEB CHALLENGES, SEMWEBEVAL 2018, 2018, 927 : 140 - 150
[2] Fine-tuning XLNet for Amazon review sentiment analysis: A comparative evaluation of transformer models
Shetty, Amrithkala M.
Manjaiah, D. H.
Aljunid, Mohammed Fadhel
ETRI JOURNAL, 2025,
[3] Cross-Domain Sentiment Analysis Based on Small in-Domain Fine-Tuning
Kotelnikova, Anastasia V.
Vychegzhanin, Sergey V.
Kotelnikov, Evgeny V.
IEEE ACCESS, 2023, 11 : 41061 - 41074
[4] A BERT Fine-tuning Model for Targeted Sentiment Analysis of Chinese Online Course Reviews
Zhang, Huibing
Dong, Junchao
Min, Liang
Bi, Peng
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2020, 29 (7-8)
[5] BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews
Nugroho, Kuncahyo Setyo
Sukmadewa, Anantha Yullian
Wuswilahaken, Haftittah Dw
Bachtiar, Fitra Abdurrachman
Yudistira, Novanto
PROCEEDINGS OF 2021 INTERNATIONAL CONFERENCE ON SUSTAINABLE INFORMATION ENGINEERING AND TECHNOLOGY, SIET 2021, 2021, : 258 - 264
[6] Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource
Kit, Yuheng
Mokji, Musa Mohd
IEEE ACCESS, 2022, 10 : 107056 - 107065
[7] Transfer Learning for Sentiment Analysis Using BERT Based Supervised Fine-Tuning
Prottasha, Nusrat Jahan
Sami, Abdullah As
Kowsher, Md
Murad, Saydul Akbar
Bairagi, Anupam Kumar
Masud, Mehedi
Baz, Mohammed
SENSORS, 2022, 22 (11)
[8] A Fine Grain Sentiment Analysis with Semantics in Tweets
Barba Gonzalez, Cristobal
Garcia-Nieto, Jose
Navas-Delgado, Ismael
Aldana-Montes, Jose F.
INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE, 2016, 3 (06): : 22 - 28
[9] Fine-Tuning Llama 3 for Sentiment Analysis: Leveraging AWS Cloud for Enhanced Performance
Shantanu Kumar
Shruti Singh
SN Computer Science, 5 (8)
[10] Fine-Tuning Transformer-Based Representations in Active Learning for Labelling Crisis Dataset of Tweets
Paul N.R.
Balabantaray R.C.
Sahoo D.
SN Computer Science, 4 (5)

← 1 2 3 4 5 →