Machine learning approaches for sentiment analysis
Machine learning approaches for sentiment analysis
复制标题
用于情感分析的机器学习方法
DOI：
10.53730/ijhs.v6ns4.6119
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
V. Vani
中科院分区：
文献类型：
--
作者：
P. Monika;Chaitanya Kulkarni;N. Harish Kumar;S. Shruthi;V. Vani
情感分析或意见挖掘是自然语言处理（NLP）的流行任务，对用户生成的文本数据执行以了解文本的方向或情感。要进行情感分析，创建准确且精确的模型至关重要，大量利用机器学习技术来构建准确的模型。深度学习和迁移学习技术已被发现具有更高的利用率和更好的结果，使它们成为世界上最受欢迎的研究领域之一。酒店和餐饮行业分析评论，以更深入地了解客户的需求、喜好和厌恶，而专家则使用 Twitter 数据和股市新闻来预测股市趋势。机器学习算法是情感分析模型最重要的部分，本调查论文分析了所有广泛使用的情感分析机器学习方法。简要介绍了情感分析方法论以及情感分析领域的结论和未来范围。
Sentiment Analysis or Opinion Mining is popular task of Natural Language Processing (NLP) performed on textual data generated by users to know the orientation or sentiment of the text. To perform Sentiment Analysis, it is critical to create an accurate and precise model, machine learning techniques are heavily utilized to build an accurate model. Deep learning and transfer learning techniques have been found to have increased utilization and better results, making them one of the most popular research areas around the world. Hotel and restaurant industries analyze reviews to obtain a deeper understanding of their client’s needs, likes and dislikes, whereas specialists use Twitter data and stock market news items to forecast stock market trends. Machine Learning algorithms are most essential part of a Sentiment Analysis model, this survey paper analyze all the widely used Machine Learning Approaches for Sentiment Analysis. A brief introduction on Methodology for Sentiment Analysis is given along with conclusion and future scope and in the field of Sentiment Analysis.