Personalized news recommendation is an important task for online news platforms to target user interests and alleviate information overload. Most existing methods leverage news contents to make recommendation due to the importance of contents to distinguish pieces of news. Although Heterogeneous Graph (HG) shows great potential in organizing and exploiting varieties of side information to boost recommendation performance in general recommender systems, and at the same time there exist rich side information in real news recommendation scenario, existing methods lack attention to utilizing HG to exploit multiple kinds of side information to enhance news recommendation accuracy. In addition, they pay no attention to providing understandable explanations to improve user satisfaction. To this end, we propose a meta explanation triplet oriented news recommendation model. Specifically, we first construct an HG to extract high-order relatedness knowledge between users and news from various side information. Then, a dedicated neural network is designed to leverage rich side information and contents in a joint way to make news recommendation. Finally, we provide user-centered and news-centered recommendation explanations for users based on meta explanation triplets. Extensive experiments on two benchmark real-world datasets show that our model could improve news recommendation performance compared with state-of-the-art methods and provide effective explanations. 

METoNR: A meta explanation triplet oriented news recommendation model

Personalized news recommendations can alleviate the information overload problem. To enable personalized recommendation, one critical step is to learn a comprehensive user representation to model her/his interests. Many existing works learn user representations from the historical clicked news articles, which reflect their existing interests. However, these approaches ignore users’ potential interests and pay less attention to news that may interest the users in the future. To address this problem, we propose a novel Graph neural news Recommendation model with user Existing and Potential interest modeling, named GREP. Different from existing works, GREP introduces three modules to jointly model users’ existing and potential interests: (1) Existing Interest Encoding module mines user historical clicked news and applies the multi-head self-attention mechanism to capture the relatedness among the news; (2) Potential Interest Encoding module leverages the graph neural network to explore the user potential interests on the knowledge graph; and (3) Bi-directional Interaction module dynamically builds a news-entity bipartite graph to further enrich two interest representations. Finally, GREP combines the existing and potential interest representations to represent the user and leverages a prediction layer to estimate the clicking probability of the candidate news. Experiments on two real-world large-scale datasets demonstrate the state-of-the-art performance of GREP.

Graph Neural News Recommendation with User Existing and Potential Interest Modeling

Some recent \textit{news recommendation} (NR) methods introduce a Pre-trained Language Model (PLM) to encode news representation by following the vanilla pre-train and fine-tune paradigm with carefully-designed recommendation-specific neural networks and objective functions. Due to the inconsistent task objective with that of PLM, we argue that their modeling paradigm has not well exploited the abundant semantic information and linguistic knowledge embedded in the pre-training process. Recently, the pre-train, prompt, and predict paradigm, called \textit{prompt learning}, has achieved many successes in natural language processing domain. In this paper, we make the first trial of this new paradigm to develop a \textit{Prompt Learning for News Recommendation} (Prompt4NR) framework, which transforms the task of predicting whether a user would click a candidate news as a cloze-style mask-prediction task. Specifically, we design a series of prompt templates, including discrete, continuous, and hybrid templates, and construct their corresponding answer spaces to examine the proposed Prompt4NR framework. Furthermore, we use the prompt ensembling to integrate predictions from multiple prompt templates. Extensive experiments on the MIND dataset validate the effectiveness of our Prompt4NR with a set of new benchmark results.

Prompt Learning for News Recommendation

Personalized news recommendation is important for users to find interesting news information and alleviate information overload. Although it has been extensively studied over decades and has achieved notable success in improving user experience, there are still many problems and challenges that need to be further studied. To help researchers master the advances in personalized news recommendation, in this article, we present a comprehensive overview of personalized news recommendation. Instead of following the conventional taxonomy of news recommendation methods, in this article, we propose a novel perspective to understand personalized news recommendation based on its core problems and the associated techniques and challenges. We first review the techniques for tackling each core problem in a personalized news recommender system and the challenges they face. Next, we introduce the public datasets and evaluation methods for personalized news recommendation. We then discuss the key points on improving the responsibility of personalized news recommender systems. Finally, we raise several research directions that are worth investigating in the future. This article can provide up-to-date and comprehensive views on personalized news recommendation. We hope this article can facilitate research on personalized news recommendation as well as related fields in natural language processing and data mining. 

/pdf/personalized-news-recommendation-methods-and-challenges-29llar6f.pdf

Personalized News Recommendation: Methods and Challenges

Personalized news recommendation aims to provide people with customized content, which can effectively improve the reading experience. Because user interests in news are diverse and changeable, how to learn accurate user representations is the core challenge in news recommendation. However, most of the previous works only apply news-level representation for user modeling directly, the views of news, such as title, abstract, and category, are only implied and compressed into a single vector of news, which makes it impossible for different views in different news to interact with each other. In this paper, we first focus on the view-level information for user modeling and propose Deep View-Temporal Interaction Network (DeepVT) for news recommendation. It mainly contains two components, i.e., 2D semi-causal convolutional neural network (SC-CNN) and multi-operator attention (MoA). SC-CNN can synthesize interaction information at the view-level and temporal information at the news-level simultaneously and efficiently. And MoA integrates different similarity operators in self-attention functions to avoid attention bias and enhance robustness. By collaboration with SC-CNN, the global interaction at the view-level becomes more sufficient. Experiments on a large-scale real-world dataset, Microsoft News Dataset (MIND), show that our model outperforms previous models in terms of all metrics significantly.

DeepVT: Deep View-Temporal Interaction Network for News Recommendation

News recommendation is very crucial for online news services to improve user experience and alleviate information overload. Precisely learning representations of news and users is the core problem in news recommendation. Existing models usually focus on implicit text information to learn corresponding representations, which may be insufficient for modeling user interests. Even if entity information is considered from external knowledge, it may still not be used explicitly and effectively for user modeling. In this paper, we propose a novel news recommendation approach, which combine explicit entity graph with implicit text information. The entity graph consists of two types of nodes and three kinds of edges, which represent chronological order, related and affiliation relationship. Then graph neural network is utilized for reasoning on these nodes. Extensive experiments on a real-world dataset, Microsoft News Dataset (MIND), validate the effectiveness of our proposed approach.

Combining Explicit Entity Graph with Implicit Text Information for News Recommendation

Knowledge graph embedding (KGE) aims to learn continuous vectors of relations and entities in knowledge graph. Recently, transition-based KGE methods have achieved promising performance, where the single relation vector learns to translate head entity to tail entity. However, this scoring pattern is not suitable for complex scenarios where the same entity pair has different relations. Previous models usually focus on the improvement of entity representation for 1-to-N, N-to-1 and N-to-N relations, but ignore the single relation vector. In this paper, we propose a novel transition-based method, TranS, for knowledge graph embedding. The single relation vector in traditional scoring patterns is replaced with synthetic relation representation, which can solve these issues effectively and efficiently. Experiments on a large knowledge graph dataset, ogbl-wikikg2, show that our model achieves state-of-the-art results.

TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation

Archaeological site text is the main carrier of archaeological data at present, which contains rich information. How to efficiently extract useful knowledge from the massive unstructured archaeological site texts is of great significance for the mining and reuse of archaeological information. According to the site information (such as name, location, cultural type, dynasty, etc.) recorded in the Chinese archaeological site text, this paper combines deep learning and natural language processing techniques to study the information extraction method for automatically obtaining the spatio-temporal information of sites. The initial construction of the corpus of Chinese archaeological site text is completed for the first time, and the corpus is input into the Bidirectional Long Short-Term Memory with Conditional Random Fields (BiLSTM-CRF) entity recognition model and Bidirectional Gated Recurrent Units with Dual Attention (BiGRU-Dual Attention) relationship extraction model for training. The F1 values of BiLSTM-CRF model and BiGRU-Dual Attention model on the test set reach 87.87% and 88.05%, respectively. The study demonstrates that the information extraction method proposed in this paper is feasible for the Chinese archaeological site texts, which promotes the establishment of knowledge graphs in archaeology and provides new methods and ideas for the development of information mining technology in archaeology.

https://www.mdpi.com/2220-9964/11/3/175/pdf?version=1646727963

Extracting Spatio-Temporal Information from Chinese Archaeological Site Text

Expert finding aims at seeking potential users to answer new questions in Community Question Answering (CQA) websites. Most existing methods focus on designing matching frameworks between questions and experts, and rely on negative sampling technology for model training. However, sampling would lose lots of useful information about experts and questions, and make these sampling-based methods suffer the bias and non-robust issues, which may lead to an insufficient matching performance for expert findings. In this paper, we propose a novel Efficient Non-sampling Expert Finding model, named ENEF, which could learn accurate representations of questions and experts from whole training data. In our approach, we adopt a rather basic question encoder and a simple matching framework, then an efficient whole-data optimization method is elaborately designed to learn the model parameters without negative sampling with rather a low space and time complexity. Extensive experimental results on four real-world CQA datasets demonstrate that our model ENEF could achieve better performance and faster training efficiency than existing state-of-the-art expert finding methods.

Qing Yang

Papers

Combining Explicit Entity Graph with Implicit Text Information for News Recommendation

TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation

DeepVT: Deep View-Temporal Interaction Network for News Recommendation

Extracting Spatio-Temporal Information from Chinese Archaeological Site Text

Efficient Non-sampling Expert Finding