Content linking for UGC based on Word Embedding model

Abstract

There are huge amounts of User Generated Contents (UGCs) consisting of authors' articles of different themes and readers' comments in social networks every day. Generally, an article often gives rise to thousands of readers' comments, which are related to specific points of the originally published article or previous comments. Hence it has suggested the urgent need for automated methods to implement the content linking task, which can also help other related applications, such as information retrieval, summarization and content management. So far content linking is still a relatively new issue. Because of the unsatisfactory of traditional ways based on feature extraction, we look forward to using deeper textual semantic analysis. The Word Embedding model based on deep learning has performed well in Natural Language Processing (NLP), especially in mining deep semantic information recently. Therefore, we study further on the Word Embedding model trained by different neural network models from which we can learn the structure, principles and training ways of the neural network based language models in more depth to complete deep semantic feature extraction. With the aid of the semantic features, we expect to put forward a new method for content linking between comments and their original articles in social networks, and finally verify the validity of the proposed method through experiments and comparison with traditional ways based on feature extraction.