Personalized search tailors document ranking lists for each individual user based on her interests and query intent to better satisfy the user’s information need. Many personalized search models have been proposed. They first build a user interest profile from the user’s search history, and then re-rank the documents based on the personalized matching scores between the created profile and candidate documents. In this article, we attempt to solve the personalized search problem from an alternative perspective of clarifying the user’s intention of the current query. We know that there are many ambiguous words in natural language such as “Apple.” People with different knowledge backgrounds and interests have personalized understandings of these words. Therefore, we propose a personalized search model with personal word embeddings for each individual user that mainly contain the word meanings that the user already knows and can reflect the user interests. To learn great personal word embeddings, we design a pre-training model that captures both the textual information of the query log and the information about user interests contained in the click-through data represented as a graph structure. With personal word embeddings, we obtain the personalized word and context-aware representations of the query and documents. Furthermore, we also employ the current session as the short-term search context to dynamically disambiguate the current query. Finally, we use a matching model to calculate the matching score between the personalized query and document representations for ranking. Experimental results on two large-scale query logs show that our designed model significantly outperforms state-of-the-art personalization models.
POI recommendation has become an essential means to help people discover attractive places. Intuitively, activities have an important impact on users’ decision-making, because users select POIs to attend corresponding activities. However, many existing studies ignore the social motivation of user behaviors and regard all check-ins as influenced only by individual user interests. As a result, they cannot model user preferences accurately, which degrades recommendation effectiveness. In this article, from the perspective of activities, this study proposes a probabilistic generative model called STARec. Specifically, based on the social effect of activities, STARec defines users’ social preferences as distinct from their individual interests and combines these with individual user activity interests to effectively depict user preferences. Moreover, the inconsistency between users’ social preferences and their decisions is modeled. An activity frequency feature is introduced to acquire accurate user social preferences because of close correlation between these and the key impact factor of corresponding check-ins. An alias sampling-based training method was used to accelerate training. Extensive experiments were conducted on two real-world datasets. Experimental results demonstrated that the proposed STARec model achieves superior performance in terms of high recommendation accuracy, robustness to data sparsity, effectiveness in handling cold-start problems, efficiency, and interpretability.
Recommendation in legal scenario (Legal-Rec) is a specialized recommendation task that aims to provide potential helpful legal documents for users. While there are mainly three differences compared with traditional recommendation: (1) Both the structural connections and textual contents of legal information are important in the Legal-Rec scenario, which means feature fusion is very important here. (2) Legal-Rec users prefer the newest legal cases (the latest legal interpretation and legal practice), which leads to a severe new-item problem. (3) Different from users in other scenarios, most Legal-Rec users are expert and domain-related users. They often concentrate on several topics and have more stable information needs. So it is important to accurately model user interests here. To the best of our knowledge, existing recommendation work cannot handle these challenges simultaneously.
To address these challenges, we propose a legal information enhanced graph neural network–based recommendation framework (LegalGNN). First, a unified legal content and structure representation model is designed for feature fusion, where the Heterogeneous Legal Information Network (HLIN) is constructed to connect the structural features (e.g., knowledge graph) and contextual features (e.g., the content of legal documents) for training. Second, to model user interests, we incorporate the queries users issued in legal systems into the HLIN and link them with both retrieved documents and inquired users. This extra information is not only helpful for estimating user preferences, but also valuable for cold users/items (with less interaction history) in this scenario. Third, a graph neural network with relational attention mechanism is applied to make use of high-order connections in HLIN for Legal-Rec. Experimental results on a real-world legal dataset verify that LegalGNN outperforms several state-of-the-art methods significantly. As far as we know, LegalGNN is the first graph neural model for legal recommendation.
The authors investigate into the rules contained in the international treaties, Russian existing laws and judicial routine related to exclusiveness of authors’ rights. The character of social changes in the digital era were specified. Several types of legal relations remain traditional, however in today’s information society has to revise existing laws in which authors rights dominate over information user interests. At the same time, the authors re underprotected from piracy. Legislators have to prioritize in the first place who and from whom must be protected in the information society: the authros from pirates, intellectual property from plagiarism, or the users from actualaccessible information. Secondly, the rights of new knowledge have to be managed and efficient ways to righ t-ful transfer of accumulated knowledge to users have to be found. Implementation of information technologies into libraries and access to digital information resources change radically the quality of library services. The authors challenged themselves with attracting attention to the problems of information society in Russia.
A web-based search system recommends and gives results such as customized image or video contents using information such as user interests, search time, and place. Time information extracted from images can be used as a important metadata in the web search system. We present an efficient algorithm to classify time period into day, dawn, and night when the input is a single image with a sky region. We employ the Mask R-CNN to extract a sky region. Based on the extracted sky region, reference color histograms are generated, which can be considered as the ground-truth. To compare the histograms effectively, we design the windowed-color histograms (for RGB bands) to compare each time period from the sky region of the reference data with one of the input images. Also, we use a weighting approach to reflect a more separable feature on the windowed-color histogram. With the proposed windowed-color histogram, we verify about 91% of the recognition accuracy in the test data. Compared with the existing deep neural network models, we verify that the proposed algorithm achieves better performance in the test dataset.
Due to the lack of domain and interface knowledge, it is difficult for users to create suitable service processes according to their needs. Thus, the paper puts forward a new service composition recommendation method. The method is composed of two steps: the first step is service component recommendation based on recurrent neural network (RNN). When a user selects a service component, the RNN algorithm is exploited to recommend other matched services to the user, aiding the completion of a service composition. The second step is service composition recommendation based on Naive Bayes. When the user completes a service composition, considering the diversity of user interests, the Bayesian classifier is used to model their interests, and other service compositions that satisfy the user interests are recommended to the user. Experiments show that the proposed method can accurately recommend relevant service components and service compositions to users.
Training models to predict click and order targets at the same time. For better user satisfaction and business effectiveness, multitask learning is one of the most important methods in e-commerce. Some existing researches model user representation based on historical behaviour sequence to capture user interests. It is often the case that user interests may change from their past routines. However, multi-perspective attention has broad horizon, which covers different characteristics of human reasoning, emotions, perception, attention, and memory. In this paper, we attempt to introduce the multi-perspective attention and sequence behaviour into multitask learning. Our proposed method offers better understanding of user interest and decision. To achieve more flexible parameter sharing and maintaining the special feature advantage of each task, we improve the attention mechanism at the view of expert interactive. To the best of our knowledge, we firstly propose the implicit interaction mode, the explicit hard interaction mode, the explicit soft interaction mode, and the data fusion mode in multitask learning. We do experiments on public data and lab medical data. The results show that our model consistently achieves remarkable improvements to the state-of-the-art method.
We propose an interpretable model that combines the simplicity of matrix factorization with the flexibility of neural networks to model evolving user interests by efficiently extracting nonlinear patterns from massive text data collections.