Decoding Sentiments: An Efficient Trans-Long Short Term Memory to Understand Viewer Reactions on Ad-Supported Video Contents
Shashishekhar Ramagundam, Niharika Karne · 2024
Viewer reaction analysis in ad-supported video content focuses on the use of advanced techniques to understand and interpret the emotional responses expressed by viewers during ad viewing experiences. This analysis goes beyond simple positive or negative sentiment and delves into the nuances of viewer reactions, allowing for a more comprehensive understanding of the emotional impact of ads. With this information, advertisers can make data-driven decisions to optimize their advertising strategies, create more engaging content, and ultimately enhance the viewer experience. One of the challenges in sentiment analysis for viewer reaction analysis is the inherent subjectivity and variability of human emotions. Emotions can be complex and subjective, making it difficult to accurately capture and interpret them solely based on text or viewer feedback. Different individuals may perceive and express emotions differently, adding another layer of complexity to the analysis process. Addressing these challenges requires a combination of advanced deep learning model refinement. Overcoming these challenges can provide valuable insights into viewer reactions, enabling advertisers and content creators to create more engaging and impactful ad-supported video content. In this paper, an Artificial Intelligence (AI)-based sentiment analysis is introduced to analyze the viewer's reaction while watching the ad in the video content. Here, an efficient model named Trans-Long Short-Term Memory (Trans-LSTM) is developed to perform the sentiment analysis. The developed Trans-LSTM is helpful in supervising the emotional data in the online video content and identifying the popularity of the corresponding video. The suggested model effectively analyzes the reviewer’s actions while watching all types of video content. Finally, the experimental analysis is performed to find the effectiveness of the developed sentiment analysis model via various metrics.