Heterogeneous Context Information Research Articles

Aspect sentiment analysis with heterogeneous graph neural networks

Aspect-based sentiment analysis technologies may be a very practical methodology for securities trading, commodity sales, movie rating websites, etc. Most recent studies adopt the recurrent neural network or attention-based neural network methods to infer aspect sentiment using opinion context terms and sentence dependency trees. However, due to a sentence often having multiple aspects sentiment representation, these models are hard to achieve satisfactory classification results. In this paper, we discuss these problems by encoding sentence syntax tree, words relations and opinion dictionary information in a unified framework. We called this method heterogeneous graph neural networks (Hete_GNNs). Firstly, we adopt the interactive aspect words and contexts to encode the sentence sequence information for parameter sharing. Then, we utilized a novel heterogeneous graph neural network for encoding these sentences’ syntax dependency tree, prior sentiment dictionary, and some part-of-speech tagging information for sentiment prediction. We perform the Hete_GNNs sentiment judgment and report the experiments on five domain datasets, and the results confirm that the heterogeneous context information can be better captured with heterogeneous graph neural networks. The improvement of the proposed method is demonstrated by aspect sentiment classification task comparison.

Attention-based explainable friend link prediction with heterogeneous context information

Friend link prediction is an important research problem in recommender systems. Existing network embedding and knowledge embedding methods mainly consider the structural relationships of entities, ignoring the explanatory role of text contents. In this paper, we present an explainable friend link recommendation method that leverages direct and indirect similarity of user pairs via fusion embedding of heterogeneous context information. In social networks, while considering user content interests, first, a fusion user embedding method was developed by incorporating external knowledge semantics. Second, for a user pair, we calculate their direct similar relationship using fusion user embeddings. Additionally, based on intermediate neighbors, we compute their indirect similar relationship by using an attention mechanism, which explains neighbors’ bootable and transitive influences for learning the social relationship of user pairs. Then, a hybrid personalized and neighbor attention model for friend link prediction was proposed by considering direct and indirect factors. Finally, experiments were conducted on the Sina Weibo datasets, which indicates that the proposed method effectively predicts the friends of users and provides a good interpretation for link prediction recommendation results.

Context Aware Sentiment Link Prediction in Heterogeneous Social Network

People often express opinions towards others in a social network, causing sentiment links to form among users. To develop effective methods for discovering implicit sentiment links among users, the extraction and exploitation of structural semantic information from heterogeneous social networks are of great importance. We propose a novel heterogeneous social network embedding-based approach for sentiment link prediction that takes both global structural information with multi-dimensional relations and heterogeneous context information into consideration to leverage rich and intrinsic association information. Specifically, the attributed heterogeneous social network and Sentic LSTM-based sentiment link network are employed to incorporate various explicit context knowledge and implicit multi-dimensional user interaction association knowledge into representation learning and sentiment link prediction. The experimental results on a real-world dataset show that the proposed approach has advantages over the state-of-the-art baselines. The results show the effectiveness of incorporating social relations and profile context information into sentiment link prediction, especially in cold-start scenarios. The learned embedding representation that incorporates both structural information with multi-dimensional relations and context information from heterogeneous social networks can improve sentiment link prediction performance. The proposed approach is effective and feasible for detecting unobserved sentiment links from online social networks and outperforms the state-of-the-art baselines in sentiment link prediction tasks.

Context-assisted face clustering framework with human-in-the-loop

Automatic face clustering, which aims to group faces referring to the same people together, is a key component for face tagging and image management. Standard face clustering approaches that are based on analyzing facial features can already achieve high-precision results. However, they often suffer from low recall due to the large variation of faces in pose, expression, illumination, occlusion, etc. To improve the clustering recall without reducing the high precision, we leverage the heterogeneous context information to iteratively merge the clusters referring to same entities. We first investigate the appropriate methods to utilize the context information at the cluster level, including using of “common scene”, people co-occurrence, human attributes, and clothing. We then propose a unified framework that employs bootstrapping to automatically learn adaptive rules to integrate this heterogeneous contextual information, along with facial features, together. Finally, we discuss a novel methodology for integrating human-in-the-loop feedback mechanisms that leverage human interaction to achieve the high-quality clustering results. Experimental results on two personal photo collections and one real-world surveillance dataset demonstrate the effectiveness of the proposed approach in improving recall while maintaining very high precision of face clustering.

Realising Dynamism in MediaSense Publish/Subscribe Model for Logical-Clustering in Crowdsourcing

The upsurge of social networks, mobile devices, Internet or Web-enabled services have enabled unprecedented level of human participation in pervasive computing which is coined as crowdsourcing. The pervasiveness of computing devices leads to a fast varying computing where it is imperative to have a model for catering the dynamic environment. The challenge of efficiently distributing context information in logical-clustering in crowdsourcing scenarios can be countered by the scalable MediaSense PubSub model. MeidaSense is a proven scalable PubSub model for static environment. However, the scalability of MediaSense as PubSub model is further challenged by its viability to adjust to the dynamic nature of crowdsourcing. Crowdsourcing does not only involve fast varying pervasive devices but also dynamic distributed and heterogeneous context information. In light of this, the paper extends the current MediaSense PubSub model which can handle dynamic logical-clustering in crowdsourcing. The results suggest that the extended MediaSense is viable for catering the dynamism nature of crowdsourcing, moreover, it is possible to predict the near-optimal subscription matching time and predict the time it takes to update (insert or delete) context-IDs along with existing published context-IDs. Furthermore, it is possible to foretell the memory usage in MediaSense PubSub model.

Context data management: an architectural framework for context-aware services

Mobile devices are equipped with increasing processing power and sensing capabilities, and mobile services can benefit from these features to provide a more personalized and context-aware experience to final users. To efficiently collect and deliver context information, a proper architecture is required, where heterogeneous context information can be processed to provide higher-level context information, context data are represented uniformly, and applications can process context data with high-level queries. This paper fulfils this goal of interoperability and domain independence by defining a framework for context data management relying on open standards (XMPP and REST), acting as an enabler for third-party context-aware applications; other main novelties of our work are the definition of a ContextML for standard context data representation, and a Context Query Language (CQL) to access context information based on high-level data filtering.