Multi-task Prompt Words Learning for Social Media Content Generation

TL;DR

This paper introduces a multi-task prompt word generation framework that fuses multi-modal data to improve social media content creation, leveraging ChatGPT for evaluation and achieving superior content quality.

Contribution

It presents a novel multi-task learning approach combining topic, sentiment, scene, and keyword analysis for prompt word generation in social media content creation.

Findings

Generated content quality surpasses manual and other cueing methods.

Multi-task framework improves content clarity and image consistency.

ChatGPT-based evaluation enables large-scale assessment.

Abstract

The rapid development of the Internet has profoundly changed human life. Humans are increasingly expressing themselves and interacting with others on social media platforms. However, although artificial intelligence technology has been widely used in many aspects of life, its application in social media content creation is still blank. To solve this problem, we propose a new prompt word generation framework based on multi-modal information fusion, which combines multiple tasks including topic classification, sentiment analysis, scene recognition and keyword extraction to generate more comprehensive prompt words. Subsequently, we use a template containing a set of prompt words to guide ChatGPT to generate high-quality tweets. Furthermore, in the absence of effective and objective evaluation criteria in the field of content generation, we use the ChatGPT tool to evaluate the results generated by the algorithm, making large-scale evaluation of content generation algorithms possible. Evaluation results on extensive content generation demonstrate that our cue word generation framework generates higher quality content compared to manual methods and other cueing techniques, while topic classification, sentiment analysis, and scene recognition significantly enhance content clarity and its consistency with the image.