News2vec: News Network Embedding with Subnode Information

Abstract

With the development of NLP technologies, news can be automatically categorized and labeled according to a variety of characteristics, at the same time be represented as low dimensional embeddings. However, it lacks a systematic approach that effectively integrates the inherited features and inter-textual knowledge of news to represent the collective information with a dense vector. With the aim of filling this gap, the News2vec model is proposed to allow the distributed representation of news taking into account its associated features. To describe the cross-document linkages between news, a network consisting of news and its attributes is constructed. Moreover, the News2vec model treats the news node as a bag of features by developing the Subnode model. Based on the biased random walk and the skip-gram model, each news feature is mapped to a vector, and the news is thus represented as the sum of its features. This approach offers an easy solution to create embeddings for unseen news nodes based on its attributes. To evaluate our model, dimension reduction plots and correlation heat-maps are created to visualize the news vectors, together with the application of two downstream tasks, the stock movement prediction and news recommendation. By comparing with other established text/sentence embedding models, we show that News2vec achieves state-of-the-art performance on these news-related tasks.

TrNews: Heterogeneous User-Interest Transfer Learning for News Recommendation

“…Content recommendation Content-based recommendation exploits the content information about items (e.g., news title and article body (Yan et al, 2012;Xiao et al, 2019;Ma et al, 2019;Wu et al, 2020;Hu et al, 2020), tag, vlog (Gao et al, 2010)), builds a profile for each user, and then matches users to items (Lops et al, 2011;Yu et al, 2016;Wu et al, 2019b). It is effective for items with content or auxiliary information but suffers from the issues of data sparsity for users.…”

Organizing Financial Opinions

“…They use a BiLSTM model to predict the relation type of the given entity pair. • Ma et al [50] link news articles by a bag of proposed features, and encode each news article into a vector. They show that this representation successfully groups related news articles, and they conduct further experiments on the downstream tasks of stock movement prediction and news recommendation.…”

Event-Driven Query Expansion

“…Most approaches treat events as textual data and apply text embedding methods [25,35,39], while others involve leveraging knowledge graph data [13], or using networks and random walks techniques [37]. The latter has also been used for creating news embeddings [22].…”