Research on Emotion Classification for Social Media Texts Based on Affective Meta-Learning

Social media platforms are becoming increasingly popular worldwide with the rapid development of the Internet power. Therefore, many users have the opportunity to communicate in various forms such as texts, emoticons, and memes on the Internet. Meanwhile, they generate a lot of affective elements while discussing events and merchandise. In the process of classifying the user's language and text, if researchers can grasp those affective elements, they can accurately understand the user's main intentions and emotional tendencies in the discussion process. The above is a major point of the current research. This paper uses an advanced approach that combines natural language processing and affective meta-learning to automatically classify emotion text on social media to accurately understand the language habits of users. This approach achieves an ideally result by analyzing the determined parameters and using neural network algorithms for text-based emotion classification.