基于TextBlob与VADER的《盗梦空间》电影评论情感分析研究
A Sentiment Analysis of Inception Movie Reviews Based on TextBlob and VADER
DOI: 10.12677/ml.2025.137707, PDF,   
作者: 王雨婷：上海海事大学外国语学院，江苏 南京
关键词: 电影评论；情感分析；自然语言处理；Movie Reviews； Sentiment Analysis； Natural Language Processing
摘要: 随着互联网技术的发展，电影评论网站积累了大量用户评论数据。对这些评论进行情感分析不仅能够帮助用户快速了解电影口碑，也为电影产业提供有价值的决策参考。本研究以电影《盗梦空间》(Inception)的英文评论数据为研究对象，采用TextBlob工具对评论数据进行情感分类，分析评论的极性分数以判断观众对该电影的情感倾向为积极或消极，同时引入VADER工具进行补充，进一步分析影评中的情绪强度分布，以增强情感分析的深度和多维度表现。研究结果表明，绝大多数评论呈现出积极情感倾向，显示《盗梦空间》在观众中具有较高的认可度。然而，也有一部分评论表达了消极情绪，主要集中在对情节复杂性和结局开放性的不满。本研究验证了TextBlob在情感分析任务中的有效性，并展示了其在电影评论情感分析中的应用价值，为电影评论情感分析提供了有效的实践方法。
Abstract: With the rapid development of internet technologies, movie review platforms have accumulated a large volume of user-generated content. Analyzing the sentiment of these reviews not only helps users quickly grasp the general reception of a film but also provides valuable insights for decision-making in the film industry. This study focuses on English-language reviews of the movie Inception and employs the TextBlob to perform sentiment classification. By analyzing the polarity scores of the reviews, the study determines whether viewers’ attitudes toward the movie are generally positive or negative. At the same time, the VADER was introduced as a supplement to further analyze the distribution of sentiment intensity in the reviews, enhancing the depth and multidimensionality of the sentiment analysis. The findings indicate that the vast majority of reviews exhibit a positive sentiment, reflecting a high level of audience approval for Inception. However, a portion of the reviews expresses negative sentiments, primarily related to dissatisfaction with the film’s complex plot and open-ended conclusion. This research confirms the effectiveness of TextBlob in sentiment analysis tasks and demonstrates its practical value in analyzing movie reviews, offering an efficient method for sentiment assessment in this domain.
文章引用：王雨婷. 基于TextBlob与VADER的《盗梦空间》电影评论情感分析研究[J]. 现代语言学, 2025, 13(7): 259-266. https://doi.org/10.12677/ml.2025.137707

参考文献

[1] 林崇德, 杨治良, 黄希庭. 心理学大辞典[M]. 上海: 上海教育出版社, 2003.
[2] Liu, B. (2012) Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers.
[3] Mohey, D. (2016) A Survey on Sentiment Analysis Challenges.
http://www.sciencedirect.com/cience/arti-cle/pii/S1018363916300071
[4] Turney, P.D. (2002) Thumbs up or Thumbs down? Semantic Orientation Applied to Unsupervised Classification of Reviews.
[5] 唐晓波, 刘广超. 细粒度情感分析研究综述[J]. 图书情报工作, 2017, 61(5): 132-140.
[6] 吴思文. 基于深度学习的电影评论情感分析方法研究[D]: [硕士学位论文]. 兰州: 西北师范大学, 2024.
[7] Whissell, C. (1998) Objective Analysis of Text: II. Using an Emotional Compass to Describe the Emotional Tone of Situation Comedies. Psychological Reports, 82, 643-646. [Google Scholar] [CrossRef] [PubMed]
[8] 李寿山, 李逸薇, 黄居仁, 等. 基于双语信息和标签传播算法的中文情感词典构建方法[J]. 中文信息学报, 2013, 27(6): 75-81.
[9] 魏慧玲. 文本情感分析在产品评论中的应用研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2014.
[10] Pang, T.B., Pang, B. and Lee, L. (2002) Thumbs up Sentiment Classification Using Machine Learning. Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, EMNLP 2002, Philadelphia, 6-7 July 2002, 79-86.
[11] Whitelaw, C., Garg, N. and Argamon, S. (2005) Using Appraisal Groups for Sentiment Analysis. Proceedings of the 14th ACM International Conference on Information and Knowledge Management, Bremen, 31 October-5 November 2005, 625-631. [Google Scholar] [CrossRef] 
[12] 徐军, 丁宇新, 王晓龙. 使用机器学习方法进行新闻的情感自动分类[J]. 中文信息学报, 2007, 21(6): 95-100.
[13] Kim, Y. (2014) Convolutional Neural Networks for Sentence Classification. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, 25-29 October 2014, 1746-1751. [Google Scholar] [CrossRef] 
[14] Zheng, J. and Zheng, L. (2019) A Hybrid Bidirectional Recurrent Convolutional Neural Network Attention-Based Model for Text Classification. IEEE Access, 7, 106673-106685. [Google Scholar] [CrossRef] 
[15] Jang, B., Kim, M., Harerimana, G., Kang, S. and Kim, J.W. (2020) Bi-LSTM Model to Increase Accuracy in Text Classification: Combining Word2vec CNN and Attention Mechanism. Applied Sciences, 10, Article No. 5841. [Google Scholar] [CrossRef] 
[16] Pandey, R. and Singh, J.P. (2022) BERT-LSTM Model for Sarcasm Detection in Code-Mixed Social Media Post. Journal of Intelligent Information Systems, 60, 235-254. [Google Scholar] [CrossRef]