Social Media Emotion Analysis in Indonesian Using Fine-Tuning BERT Model

机译：使用微调BERT模型印度尼西亚的社交媒体情感分析

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Social media is the leading platform were users’ express opinions and emotions. Emotion Analysis aims to identify emotions: happy, sad, angry, fear, disgust, shame, and guilt. InaMoodMeter framework takes the unstructured status of a Facebook user. It processes it to extract emotion from teenage users for self-assessment and to observe emotion related to online customer satisfaction. We also created an Indonesian Dataset for Emotion Analysis from Facebook. The dataset can be utilized as a valuable benchmark for emotion classification in Indonesian. With this dataset, many state-of-the-art approaches are evaluated. We also experimented on the ISEAR Indonesian translated dataset. This research consists of two stages: obtaining training data to build the dataset and performing classification. Our proposed method can achieve the highest accuracy of 79% with the Fine-Tuning Bert Model.

机译：社交媒体是领先的平台，是用户的表达意见和情绪。情感分析旨在识别情绪：快乐，悲伤，愤怒，恐惧，厌恶，羞耻和内疚。难以追求Facebook用户的非结构化状态。它处理它以从青少年用户提取自我评估的情绪，并观察与在线客户满意度相关的情感。我们还从Facebook创建了一个用于情感分析的印度尼西亚数据集。数据集可以用作印度尼西亚情感分类的有价值基准。使用此数据集，评估了许多最先进的方法。我们还在Irsear印度尼西亚翻译的数据集中试验。本研究包括两个阶段：获取培训数据以构建数据集并执行分类。我们所提出的方法可以通过微调BERT模型达到79％的最高精度。

著录项

来源
《East Indonesia Conference on Computer and Information Technology》|2021年|334-337|共4页
会议地点
作者
Esther Irawati Setiawan; Lukas Kristianto; Arya Tandy Hermawan; Joan Santoso; Kimiya Fujisawa; Mauridhi Hery Purnomo;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Support vector machines; Deep learning; Social networking (online); Computational modeling; Bit error rate; Customer satisfaction; Training data;

机译：支持向量机;深度学习;社交网络（在线）;计算建模;误码率;客户满意度;培训数据;

相似文献

外文文献
中文文献
专利

1. Analysis of associations between emotions and activities of drug users and their addiction recovery tendencies from social media posts using structural equation modeling [J] . Deeptanshu Jha, Rahul Singh BMC Bioinformatics . 2020,第18期

机译：使用结构方程建模的社交媒体柱情绪与吸毒与瘾恢复趋势的关联分析
2. Stance detection with BERT embeddings for credibility analysis of information on social media [J] . Hema Karande, Rahee Walambe, Victor Benjamin, PeerJ Computer Science . 2021,第a期

机译：使用BERT Embeddings的立场检测，以便于社交媒体信息的信誉分析
3. Hate speech detection and racial bias mitigation in social media based on BERT model [J] . Marzieh Mozafari, Reza Farahbakhsh, No?l Crespi PLoS One . 2020,第8期

机译：基于BERT模型的社交媒体讨厌讲话检测和种族偏见缓解
4. UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models [C] . Mircea-Adrian Tanase, Dumitru-Clementin Cercel, Costin-Gabriel Chiru International Workshop on Semantic Evaluation . 2020

机译：在Semeval-2020的UPB任务12：通过微调各种基于BERT的型号来社交媒体对社交媒体的多语言攻击性语言检测
5. Stress, emotion regulation, and social competence in high-risk children: Testing moderator and mediator models via structural equation modeling. [D] . Amlund Hagen, Kristine. 2004

机译：高危儿童的压力，情绪调节和社交能力：通过结构方程模型测试主持人和调解人模型。
6. Analysis of associations between emotions and activities of drug users and their addiction recovery tendencies from social media posts using structural equation modeling [O] . Deeptanshu Jha, Rahul Singh 2020

机译：使用结构方程建模的社交媒体柱情绪与吸毒与瘾恢复趋势的关联分析
7. Analysis of associations between emotions and activities of drug users and their addiction recovery tendencies from social media posts using structural equation modeling [O] . Deeptanshu Jha, Rahul Singh 2020

机译：使用结构方程建模的社交媒体柱情绪与吸毒与瘾恢复趋势的关联分析

Social Media Emotion Analysis in Indonesian Using Fine-Tuning BERT Model

摘要

著录项

相似文献

相关主题

期刊订阅