Convolutional Neural Networks (CNNs) have been recently introduced in the domain of session-based next item recommendation. An ordered collection of past items the user has interacted with in a session (or sequence) are embedded into a 2-dimensional latent matrix, and treated as an image. The convolution and pooling operations are then applied to the mapped item embeddings. In this paper, we first examine the typical session-based CNN recommender and show that both the generative model and network architecture are suboptimal when modeling long-range dependencies in the item sequence. To address the issues, we introduce a simple, but very effective generative model that is capable of learning high-level representation from both short-and long-range item dependencies. The network architecture of the proposed model is formed of a stack of holed convolutional layers, which can efficiently increase the receptive fields without relying on the pooling operation. Another contribution is the effective use of residual block structure in recommender systems, which can ease the optimization for much deeper networks. The proposed generative model attains state-of-the-art accuracy with less training time in the next item recommendation task. It accordingly can be used as a powerful recommendation baseline to beat in future, especially when there are long sequences of user feedback. ACM Reference Format:

Social network systems, like last.fm, play a significant role in Web 2.0, containing large amounts of multimedia-enriched data that are enhanced both by explicit user-provided annotations and implicit aggregated feedback describing the personal preferences of each user. It is also a common tendency for these systems to encourage the creation of virtual networks among their users by allowing them to establish bonds of friendship and thus provide a novel and direct medium for the exchange of data.We investigate the role of these additional relationships in developing a track recommendation system. Taking into account both the social annotation and friendships inherent in the social graph established among users, items and tags, we created a collaborative recommendation system that effectively adapts to the personal information needs of each user. We adopt the generic framework of Random Walk with Restarts in order to provide with a more natural and efficient way to represent social networks.In this work we collected a representative enough portion of the music social network last.fm, capturing explicitly expressed bonds of friendship of the user as well as social tags. We performed a series of comparison experiments between the Random Walk with Restarts model and a user-based collaborative filtering method using the Pearson Correlation similarity. The results show that the graph model system benefits from the additional information embedded in social knowledge. In addition, the graph model outperforms the standard collaborative filtering method.

In this article, we investigate the criteria used by online searchers when assessing the relevance of Web pages for information-seeking tasks. Twenty-four participants were given three tasks each, and they indicated the features of Web pages that they used when deciding about the usefulness of the pages in relation to the tasks. These tasks were presented within the context of a simulated work-task situation. We investigated the relative utility of features identified by participants (Web page content, structure, and quality) and how the importance of these features is affected by the type of information-seeking task performed and the stage of the search. The results of this study provide a set of criteria used by searchers to decide about the utility of Web pages for different types of tasks. Such criteria can have implications for the design of systems that use or recommend Web pages. IntroductionInformation retrieval (IR) systems aim to provide users with information that will help them in relation to the information need that they expressed to the system (typically in the form of a query). Searchers are then usually involved in the process of evaluating the utility (or the relevance) of the information (i.e., documents) that the IR system retrieves. One of the most common information-seeking situations entails the use of an Internet search engine (Jansen, Spink, & Saracevic, 2000). The availability of information on the World Wide Web (WWW) has established search engines as a major tool for IR and Web documents as a popular medium through which users access information.Assessing the utility of information in relation to an information need is a common task for online searchers. Studies on peoples' perceptions of the relevance of information demonstrate that a range of factors affect human judgements of relevance (e.g., Barry, 1994Barry, , 1998Cool, Belkin, & Kantor, 1993;Maglaughlin & Sonnenwald, 2002;Schamber, 1991). However, such studies often only consider formal textual documents such as journal and conference articles rather than the wide range of formally and informally produced multimedia documents found on the Web. The nature of the IR task on the WWW is different from that on more traditional IR systems (Jansen et al., 2000). One of the differences is the idiosyncrasy of the Web documents themselves. There is generally a large degree of variability in the quality, authority, and layout of Web pages. Moreover, the type of elements such pages contain (e.g., text, multimedia, links) can also vary to a large degree (Woodruff, Aoki, Brewer, Gauthier, & Rowe, 1996), creating a heterogeneous collection of documents distributed over distinct geographic areas.The motivation behind this study was to gain a better understanding of what features make a Web document useful for information seeking. We concentrated specifically on information-seeking tasks-finding Web pages that contain relevant or useful information-because this is one of the prominent uses of Web pages. It is also a task for which there exist ma...

Despite the popularity of Twitter for research, there are very few publicly available corpora, and those which are available are either too small or unsuitable for tasks such as event detection. This is partially due to a number of issues associated with the creation of Twitter corpora, including restrictions on the distribution of the tweets and the difficultly of creating relevance judgements at such a large scale. The difficulty of creating relevance judgements for the task of event detection is further hampered by ambiguity in the definition of event. In this paper, we propose a methodology for the creation of an event detection corpus. Specifically, we first create a new corpus that covers a period of 4 weeks and contains over 120 million tweets, which we make available for research. We then propose a definition of event which fits the characteristics of Twitter, and using this definition, we generate a set of relevance judgements aimed specifically at the task of event detection. To do so, we make use of existing state-of-the-art event detection approaches and Wikipedia to generate a set of candidate events with associated tweets. We then use crowdsourcing to gather relevance judgements, and discuss the quality of results, including how we ensured integrity and prevented spam. As a result of this process, along with our Twitter corpus, we release relevance judgements containing over 150,000 tweets, covering more than 500 events, which can be used for the evaluation of event detection approaches.

In session-based or sequential recommendation, it is important to consider a number of factors like long-term user engagement, multiple types of user-item interactions such as clicks, purchases etc. The current state-of-the-art supervised approaches fail to model them appropriately. Casting sequential recommendation task as a reinforcement learning (RL) problem is a promising direction. A major component of RL approaches is to train the agent through interactions with the environment. However, it is often problematic to train a recommender in an on-line fashion due to the requirement to expose users to irrelevant recommendations. As a result, learning the policy from logged implicit feedback is of vital importance, which is challenging due to the pure off-policy setting and lack of negative rewards (feedback).In this paper, we propose self-supervised reinforcement learning for sequential recommendation tasks. Our approach augments standard recommendation models with two output layers: one for selfsupervised learning and the other for RL. The RL part acts as a regularizer to drive the supervised layer focusing on specific rewards (e.g., recommending items which may lead to purchases rather than clicks) while the self-supervised layer with cross-entropy loss provides strong gradient signals for parameter updates. Based on such an approach, we propose two frameworks namely Self-Supervised Qlearning (SQN) and Self-Supervised Actor-Critic (SAC). We integrate the proposed frameworks with four state-of-the-art recommendation models. Experimental results on two real-world datasets demonstrate the effectiveness of our approach. CCS CONCEPTS• Information systems → Recommender systems; Retrieval models and ranking; Novelty in information retrieval.