SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction
By Hongwei Wang, Fuzheng Zhang, Min Hou, Xing Xie, Minyi Guo, Qi Liu. 2017
343 citations recorded by the source corpus.
In online social networks people often express attitudes towards others, which forms massive sentiment links among users. Predicting the sign of sentiment links is a fundamental task in many areas such as personal advertising and public opinion analysis. Previous works mainly focus on textual sentiment classification, however, text information can only disclose the "tip of the iceberg»» about users» true opinions, of which the most are unobserved but implied by other sources of information such as social relation and users» profile. To address this problem, in this paper we investigate how to predict possibly existing sentiment links in the presence of heterogeneous information. First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users» sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method. Then we propose a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users» latent representations from heterogeneous networks and predict the sign of unobserved sentiment links. SHINE utilizes multiple deep autoencoders to map each user into a low-dimension feature space while preserving the network structure. We demonstrate the superiority of SHINE over state-of-the-art baselines on link prediction and node recommendation in two real-world datasets. The experimental results also prove the efficacy of SHINE in cold start scenario.
Subfields: Artificial Intelligence, Sentiment & Opinion Analysis, Knowledge Graphs & Representation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Sentiment & Opinion Analysis
In Knowledge Graphs & Representation
Citations in the corpus
- Knowledge Graph Convolutional Networks for Recommender Systems (2019, background): “ddress these limitations, researchers usually turn to feature-rich scenarios, where attributes of users and items are used to compensate for the sparsity and improve the performance of recommendation [3, 17]. A few recent studies [9, 18, 19, 22–24] have gone a step further than simply using attribut”
- RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, methodology): “sts in his ripple sets. As shown in Figure 2, each item vis associated with an item embedding v ∈Rd, where d is the dimension of embeddings. Item embedding can incorporate one-hot ID [11], attributes [32], bagof-words [33] or context information [25] of an item, based on the application scenario. Gi”
- DKN: Deep Knowledge-Aware Network for News Recommendation (2018, methodology): “In addition to the aforementioned DSSM [16], DeepWide [6], DeepFM [13], YouTubeNet [8] and DMF [50], other popular deep-learning-based recommender systems include Collaborative Deep Learning [44], SHINE [45], Multi-view Deep Learning [11], and Neural Collaborative Filtering [14].”
- A Survey on Knowledge Graph-Based Recommender Systems (2020, background): “Wang et al. [68] proposed SHINE, which takes the celebrity recommendation task as the sentiment link prediction task between entities in the graph.”
- Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, background): “nnnnnnn side information in recommender systems, including social networks [10], attributes [30], and multimedia (e.”
- Signed Graph Convolutional Networks (2018, methodology): “Recently a signed heterogeneous network embedding algorithm, SHINE [29], had been developed, but in their work the social network itself is unsigned and thus leaving their method not applicable to the traditional signed network embedding problem.”
- GraphGAN: Graph Representation Learning with Generative Adversarial Nets (2017, methodology): “…have examined applying representation learning methods to various types of graphs, such as weighted graphs (Grover and Leskovec 2016), directed graphs (Zhou et al. 2017), signed graphs (Wang et al. 2017b), heterogeneous graphs (Wang et al. 2018), and attributed graphs (Huang, Li, and Hu 2017).”
- Network Representation Learning: A Survey (2017, background): “Some studies [122], [123], [124] tackle signed network representation learning through directly modeling the polar of links.”
- Graph embedding on biomedical networks: methods, applications and evaluations (2019, methodology): “tails). of graphs, and thus can be used as features in building machine learning models for various downstream tasks, such as link prediction, community detection, node classification, and clustering (Wang et al., 2018; Xie et al., 2016). However, to date, these advanced approaches are mainly evaluat”
- Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems (2019, background): “vetroublerecommendingbrandnewitemsthat have not yet been heavily explored by the users. The sparsity issue can be addressed by introducing additional sources of information such as user/item profiles [23] or social networks [22]. Knowledge graphs (KGs) capture structured information and relations be”