Academic Journal

Affective Decision-Making and Perplexity in Digital Media Social Behavior Based on NLP and CLIP.

Bibliographic Details
Title: Affective Decision-Making and Perplexity in Digital Media Social Behavior Based on NLP and CLIP.
Authors: Lu, Jin1 (AUTHOR) lujin0808@szpu.edu.cn
Source: International Journal of High Speed Electronics & Systems. Sep2026, Vol. 35 Issue 4, p1-20. 20p.
Subject Terms: *Natural language processing, *Data analysis, *Decision making, *Consumer profiling, *Sentiment analysis, Machine learning, Digital media, Social psychology
Abstract: The digital media social behavior decision analysis method based on large-scale emotional data is a complex process involving natural language processing, data mining, machine learning, in-depth learning and other fields. In digital media social behavior data collection, NLP and CLIP are mainly used to process and analyze user-generated content, including multimedia data such as text, images and videos. These data come from various social media platforms, such as Weibo, WeChat, Jitterbug, Instagram, Twitter and so on. Based on the NLP and CLIP model, this paper analyzes the user's social behavior data (such as publishing content, interaction records and attention relationship), and constructs the user's accurate portrait. The content of the portrait includes the user's interest, preference, emotional tendency and so on, which realizes the group decision-making judgment for the user. At the same time, by analyzing the influence of users on social media (such as the number of fans, the number of re-tweets and the number of likes), the impact of their comments on other people's emotions and behavior is evaluated. Finally, the sentiment tendency of the user's comment text is judged by a predefined vocabulary list (such as a sentiment dictionary) and grammar rules. The experimental results show that the model based on NLP and CLIP proposed in this paper can scientifically analyze the behavior decisions of digital media users. Compared with the existing models, it greatly improves the computing speed and decision evaluation efficiency on the basis of limited computing resources. After experimental testing, the optimal solution probability of the model proposed in this paper is 0.96, which achieves the level of excellent models in the industry without the need for large-scale computational resources. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of High Speed Electronics & Systems is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Business Source Index
Description
ISSN:01291564
DOI:10.1142/S0129156425403882