An Overview of the Application of Convolutional Neural Networks inSentiment Analysis
DOI:
https://doi.org/10.61173/t4sg2v25Keywords:
Natural Language Processing, Convolutional Neural Networks, Sentiment Analysis, Artificial IntelligenceAbstract
The field of natural language processing, or NLP, uses its understanding of human language to find practical solutions to issues. It mainly includes two parts: the core task and the application. The core task represents the common problem that needs to be solved in various natural language application directions. It includes language models, morphology, grammar analysis, semantic analysis, etc. At the same time, the application section focuses on specific natural language processing tasks such as machine translation, information retrieval, question-answering systems, dialogue systems, etc. Natural language processing has made a significant contribution to the development of human society and the economy and provides strong support for all aspects of research work. Opinion mining, or sentiment analysis, is a subfield of natural language processing that develops systems for identifying and extracting ideas from text. Sentiment analysis is a hot topic since it has many practical applications. Many opinion-expressing texts are available on review sites, forums, blogs, and social media as the amount of publicly available information on the Internet grows. This unstructured information can then be automatically transformed into structured data about products, services, brands, politics, or other topics on which people can express their opinions using sentiment analysis systems. This information can be used for marketing analytics, public relations, product reviews, network sponsor ratings, product feedback, and customer service. With the rapid growth of labeled sample data sets and the notable enhancement in graphics processor (GPU) performance, convolutional neural network research has advanced rapidly and achieved remarkable leads to various computer vision tasks. By reviewing the application of CNN, we see that convolutional operations are naturally suitable for some text processing and, thus, naturally suitable for the background of sentiment analysis.
References
improvement in accuracy when compared to the original [1] Chao, C., Qi, F., (2019)The Development of Convolutional two methods of sentiment analysis (sentiment analysis Neural Networks and Their Applications in Computer Vision. based on dictionary and sentiment analysis based on Computer Science, No.03: 63-73.
machine learning). It is faster and more widely used. In [2] Changshun, D., Lei, H., (2017)Application of Segmented other words, a single convolutional neural network model Convolutional Neural Networks in Text Sentiment Analysis. can solve all aspects of emotion analysis that previously Computer Engineering & Science, No.01:173-179.
required multiple models to complete, providing a [3] Bochao, D., Jiwei, Q., (2022) Application of Adaptive convenient, efficient, and accurate path for the entire Convolutional Neural Networks in Sentiment Analysis. General emotion analysis work and encouraging the development Technology, No.02:193-196.
of the entire emotion analysis work. [4] Ping, L., Yueming, D., (2018) Application of Dual Channel Convolutional Neural Network in Text Sentiment Analysis. 5. Conclusion Computer Applications, No.06:1542-1546.
Convolutional neural networks are still not flawless and [5] Qing, Y., Li, Z., Yawen, Z., Tao, W., (2021) The Application have the following flaws: of Graph Convolutional Neural Network in Emotion Analysis of (1) Counterpropagating Chinese Dialogue. Software Guide, No.03:7-12.
Due to its high data requirements, the backpropagation [6] Yizhibuchuxidechengxuyuan (CSDN), 2020. Features and algorithm could be more efficient for deep learning. Defects of Convolutional Neural Network. https://blog.csdn.net/ (2) Translation Invariance qq_43232556/article/details/106797898.
Translation invariance describes the possibility that [7] Dazhiruoyu (CSDN), 2016. Sentiment Analysis of Short neurons that recognize an object will not fire when its Text. orientation or position is slightly altered. When a neuron https://blog.csdn.net/zbc1090549839/article/details/52800441.
is trained to identify a cat, its parameters will vary in [8] Wuhu648 (CSDN), 2021. History of Artificial Intelligence -- response to its movements and rotations. Although data Convolutional Neural networks. augmentation has helped somewhat, the problem is still https://blog.csdn.net/WUHU648/article/details/122221915 present. [9] Xinxin Lu (Liaoning Technical University), 2017. (3) Pooling Layer Application and Research of Convolutional Neural Networks in When a pooling layer is present, there may be a significant Emotion Classification. loss of essential data and an oversight of the relationship https://kns.cnki.net/kcms2/article/abstract?v=j6HAoO1nZAzZll between the part and the whole. For instance, a face GdfcV0VwNbUMhNKk1R14nYKbPSfdhVBf2ARR4REkxzgfn detector requires us to combine the mouth, eyes, nose, erOFpezalyvbPFreX1aPhRIvMP3b-70WlF9YsJpvsWVio72GPk and face contours to identify the face. CNN determines HIwW96QisGsJ62fczu8dOhSb_pFKEjf3RfByF8DgA==&unipl that it is a human face if these five features are present atform=NZKPT&language=CHS
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
