It is generally accepted that collaborative information is important for the performance of recommender systems. It is also generally accepted that if this information is sparser, it impacts recommendation systems negatively. Various approaches have tried to lift this problem by employing side information. However, global patterns that can be provided by clusters of similar items and users or even additional information such as text are often not used together with collaborative information. We study the impact of integrating clustering embeddings, review embeddings, and their combinations with embeddings obtained by a recommender system. We study the performance of this approach across various state-of-the-art recommender system algorithms including graph-based methods. We highlight that graph structures are important with sparser datasets and both, in knowledge graphs with side information as well as in collaborative bipartite graphs. In less sparse datasets, a collaborative bipartite graph is usually sufficient. We also highlight that the improvement of recommendation performance through clustering, particularly evident when combined with review embeddings is most visible on sparser data, while on less sparse data incorporating review embeddings may be sufficient when combined with one of the graph-based methods, or otherwise when combined with clustering in other methods.

Yelp Open Dataset (YOD) is a widely used dataset for Recommender Systems (RS). Multiple Knowledge Graphs (KGs) have been built for YOD, but they have various issues: the conversion processes usually do not follow state-of-the-art methodologies, fail to properly link to other KGs, do not link to existing vocabularies, ignore important data, and are generally of small size. Instead, we present the Yelp Collaborative Knowledge Graph (YCKG), where we correctly integrating taxonomies, product categories, business locations, and the Yelp social network, through common practices within the semantic web community, overcoming all these issues. As a result, the YCKG includes 150k businesses and 16.9M reviews from 1.9M distinct real users, resulting in over 244 million triples, 144 distinct predicates, for about 72 million resources, with an average in-degree and out-degree of 3.3 and 12.2, respectively. Further, we release both the data and the code used to generate the KG for inspection and further extensions. This dataset can be used to develop and test both recommendation and data-mining algorithms able to exploit rich and semantically meaningful knowledge. We publicize the code for the CKG construction on: https://github.com/MadsCorfixen/The-Yelp-Collaborative-Knowledge-Graph.

Abstract Usually, recommender systems are trained on a set of users and items and then used to recommend new user-item pairings among those seen during training. As users and items are added continuously, there is a pressing need to provide recommendations for new users and items, i.e., for users and items not seen during training. Solutions to this problem exploit techniques like meta-learning or auxiliary information encoded in knowledge graphs to learn an “inductive bias”. Yet, most existing works can either recommend for new users or new items not seen during training but not both. Further, existing methods have rarely been compared to each other. Finally, existing evaluations of these methods use a random split of training data, and thus do not consider temporal splits of ratings in training and testing. This setting ensures testing is correctly performed on user interactions that actually occur after the training period. In this paper, we propose a framework for training and testing the methods on three real world datasets, and perform a deeper analysis of each dataset to better understand the effect of emerging popularity trends. As a result, our re-evaluation of state-of-the-art methods identifies strong architectures and solutions for inductive recommendation. We find that inductive methods that perform aggregation are able to outperform non-aggregating methods in all settings; performances vary greatly across settings, pointing to new important research questions.

Inductive Recommender Systems are capable of recommending for new users and with new items thus avoiding the need to retrain after new data reaches the system. However, these methods are still trained on all the data available, requiring multiple days to train a single model, without counting hyperparameter tuning. In this work we focus on graph-based recommender systems, i.e., systems that model the data as a heterogeneous network. In other applications, graph sampling allows to study a subgraph and generalize the findings to the original graph. Thus, we investigate the applicability of sampling techniques for this task. We test on three real world datasets, with three state-of-the-art inductive methods, and using six different sampling methods. We find that its possible to maintain performance using only 50% of the training data with up to 86% percent decrease in training time; however, using less training data leads to far worse performance. Further, we find that when it comes to data for recommendations, graph sampling should also account for the temporal dimension. Therefore, we find that if higher data reduction is needed, new graph based sampling techniques should be studied and new inductive methods should be designed.

Knowledge Graphs (KGs) have been integrated in several models of recommendation to augment the informational value of an item by means of its related entities in the graph. Yet, existing datasets only provide explicit ratings on items and no information is provided about users' opinions of other (non-recommendable) entities. To overcome this limitation, we introduce a new dataset, called the MindReader dataset, providing explicit user ratings both for items and for KG entities. In this first version, the MindReader dataset provides more than 102 thousands explicit ratings collected from 1,174 real users on both items and entities from a KG in the movie domain. This dataset has been collected through an online interview application that we also release as open source. As a demonstration of the importance of this new dataset, we present a comparative study of the effect of the inclusion of ratings on non-item KG entities in a variety of state-of-the-art recommendation models. In particular, we show that most models, whether designed specifically for graph data or not, see improvements in recommendation quality when trained on explicit non-item ratings. Moreover, for some models, we show that non-item ratings can effectively replace item ratings without loss of recommendation quality. This finding, in addition to an observed greater familiarity from users towards certain descriptive entities than movies, motivates the use of KG entities for both warm and cold-start recommendations.

In this work we present a corpus for the evaluation of sensitive information detection approaches that addresses the need for real world sensitive information for empirical studies. Our sentence corpus contains different notions of complex sensitive information that correspond to different aspects of concern in a current trial of the Monsanto company. This paper describes the annotations process, where we both employ human annotators and furthermore create automatically inferred labels regarding technical, legal and informal communication within and with employees of Monsanto, drawing on a classification of documents by lawyers involved in the Monsanto court case. We release corpus of high quality sentences and parse trees with these two types of labels on sentence level. We characterize the sensitive information via several representative sensitive information detection models, in particular both keyword-based (n-gram) approaches and recent deep learning models, namely, recurrent neural networks (LSTM) and recursive neural networks (RecNN). Data and code are made publicly available.

The postoperative health status of an obesity patient indicates the outcome of the surgical treatment. By each postoperative revisit, physicians need to go through the previous patient records to recall the patient status and to evaluate the postoperative risk of readmission. In order to support in this process, we develop a method to extract indicators and to analyse weight changes, so that potential complications and risks of clinical readmission can be recognized timely. In this paper, we will compare two approaches that are based on traditional machine learning and neural networks. Relevant aspects referring to a health status change or treatment-relevant aspects are extracted from the outpatient medical records as they are generated for each postoperative revisit. The performance of traditional machine learning on the task of obesity-related entity extraction is compared with one variation of attentive recurrent neural networks. The ensemble classifier of binary attentive bi-LSTM with the data balancing using conditional generative adversarial networks (CGAN) has achieved F1 measure of 86.5% on the task of classification of eight classes of obesity-related entities. We conclude that for processing a small data set using neural networks, a data balancing method should firstly be applied to achieve an extended corpus and a general representation, which can apparently increase the differentiability of the input data. A fine-tuning in the networks can provide further enhancement of the performance.

Context-aware recommender systems consider contextual features as additional information to predict user's preferences. For example, the recommendations could be based on time, location, or the company of other people. Among the contextual information, time became an important feature because user preferences tend to change over time or be similar in the near future. Researchers have proposed different models to incorporate time into their recommender system, however, the current models are not able to capture specific temporal patterns. To address the limitation observed in previous works, we propose Collective embedding for Neural Context-Aware Recommender Systems (CoNCARS). The proposed solution jointly model the item, user and time embeddings to capture temporal patterns. Then, CoNCARS use the outer product to model the user-item-time correlations between dimensions of the embedding space. The hidden features feed our Convolutional Neural Networks (CNNs) to learn the non-linearities between the different features. Finally, we combine the output from our CNNs in the fusion layer and then predict the user's preference score. We conduct extensive experiments on real-world datasets, demonstrating CoNCARS improves the top-N item recommendation task and outperform the state-of-the-art recommendation methods.

Large vehicle trajectory data sets can give detailed insight into traffic and congestion that is useful for routing as well as transportation planning. Making information from such data sets available to more users can enable applications that reduce travel time and fuel consumption. However, extracting such information efficiently requires deep knowledge of the underlying schema and indexing methods. To enable more users to extract information from trajectory data, we have developed an API that removes the need to be familiar with the schema. Furthermore, when giving access to trajectory data, privacy concerns often call for the application of anonymization methods before analysis results are made available. In our demonstration, owners of trajectory data are able to experiment with different levels of anonymization to see how this affects the quality of different types of trajectory analysis services implemented on top of a large trajectory data set.

Location-based social networks (LBSN) are social networks complemented with users' location data, such as geo-tagged activity data. Predicting such activities finds application in marketing, recommendation systems, and logistics management. In this paper, we exploit LBSN data to predict future visitors at given locations. We fetch the travel history of visitors by their check-ins in LBSNs and identify five features that significantly drive the mobility of a visitor towards a location: (i) historic visits, (ii) location category, (iii) time, (iv) distance, and (v) friends' activities. We provide a visitor prediction model, CMViP, based on collective matrix factorization and influence propagation. CMViP first utilizes collective matrix factorization to map the first four features to a common latent space to find visitors having a significant potential to visit a given location. Then, it utilizes an influence-mining approach to further incorporate friends of those visitors, who are influenced by the visitors' activities and likely to follow them. Our experiments on two real-world data-sets show that our methods outperform the state of art in terms of precision and accuracy.

Explainable recommender systems aim to generate explanations for users according to their predicted scores, the user’s history and their similarity to other users. Recently, researchers have proposed explainable recommender models using topic models and sentiment analysis methods providing explanations based on user’s reviews. However, such methods have neglected improvements in natural language processing, even if these methods are known to improve user satisfaction. In this paper, we propose a neural explainable collective nonnegative matrix factorization (NECoNMF) to predict ratings based on users’ feedback, for example, ratings and reviews. To do so, we use collective non-negative matrix factorization to predict user preferences according to different features and a natural language model to explain the prediction. Empirical experiments were conducted in two datasets, showing the model’s efficiency for predicting ratings and generating explanations. The results present that NECoNM F improves the accuracy for explainable recommendations in comparison with the state-of-art method in 18.3% for NDCG@5, 12.2% for HitRatio@5, 17.1% for NDCG@10, and 12.2% for HitRatio@10 in the Yelp dataset. A similar performance has been observed in the Amazon dataset 7.6% for NDCG@5, 1.3% for HitRatio@5, 7.9% for NDCG@10, and 3.9% for HitRatio@10.

Leak of sensitive information from unstructured text documents is a costly problem both for government and for industrial institutions. Traditional approaches for data leak prevention are commonly based on the hypothesis that sensitive information is reflected in the presence of distinct sensitive words. However, for complex sensitive information, this hypothesis may not hold. Our TABOO system detects complex sensitive information in text documents by learning the semantic and syntactic structure of text documents. Our approach is based on natural language processing methods for paraphrase detection, and uses recursive neural networks to assign sensitivity scores to the semantic components of the sentence structure. The demonstration of TABOO focuses on interactive detection of sensitive information with the TABOO system. Users may work with real documents, alter documents or prepare free text, and subject it to information detection. TABOO allows users to work with our TABOO engine or with traditional approaches, and to compare results. Users may verify that single words can change sensitivity according to context, thereby giving hands-on experience with complex cases of sensitive information.

Influence maximization in a social network involves identifying an initial subset of nodes with a pre-defined size in order to begin the information diffusion with the objective of maximizing the influenced nodes. In this study, a sign-aware cascade (SC) model is proposed for modeling the effect of both trust and distrust relationships on activation of nodes with positive or negative opinions towards a product in the signed social networks. It is proved that positive influence maximization is NP-hard in the SC model and influence function is neither monotone nor submodular. For solving this NP-hard problem, a particle swarm optimization (PSO) method is presented which applies the random keys representation technique to convert the continuous search space of the PSO to the discrete search space of this problem. To improve the performance of this PSO method against premature convergence, a re-initialization mechanism for portion of particles with poorer fitness values and a heuristic mutation operator for global best particle are proposed. Experiments establish the effectiveness of the SC in modeling the real-world cascades. In addition, PSO method is compared with the well-known algorithms in the literature on two real-world data sets. The evaluation results demonstrate that the proposed method outperforms the compared algorithms significantly in the SC model.

Active users of Twitter are often overwhelmed with the vast amount of tweets. In this work we attempt to help users browsing a large number of accumulated posts. We propose a personalized word cloud generation as a means for users' navigation. Various user past activities such as user published tweets, retweets, and seen but not retweeted tweets are leveraged for enhanced personalization of word clouds. The best personalization results are attained with user past retweets. However, users' own past tweets are not as useful as retweets for personalization. Negative preferences derived from seen but not retweeted tweets further enhance personalized word cloud generation. The ranking combination method outperforms the preranking approach and provides a general framework for combined ranking of various user past information for enhanced word cloud generation. To better capture subtle differences of generated word clouds, we propose an evaluation of word clouds with a mean average precision measure.

Problem-Based Learning (PBL) has often been seen as an all-or-nothing approach, difficult to apply in traditional curricula based on traditional lectured courses with exercise and lab sessions. Aalborg University has since its creation in 1974 practiced PBL in all subjects, including computer science and software engineering, following a model that has become known as the Aalborg Model. Following a strategic decision in 2009, the Aalborg Model has been reshaped. We first report on the software engineering program as it was in the old Aalborg Model. We analyze the programme wrt competence levels according to Bloom’s taxonomy and compare it with the expected skills and competencies for an engineer passing a general software engineering 4-year program with an additional 4 years of experience as defined in the IEEE Software Engineering Body of Knowledge (SWEBOK) [Abran et al. 2004]. We also compare with the Graduate Software Engineering 2009 Curriculum Guidelines for Graduate Degree Programmes in Software Engineering (GSwE2009) [Pyster 2009]. We then describe the new curriculum and draw some preliminary conclusions based on analyzing the curriculum according to Bloom’s taxonomy and the results of running the program for 2 years. As the new program is structured to be compliant with the Bologna Process and thus presents all activities in multipla of 5 European Credit Transfer System points, we envision that elements of the program could be used in more traditional curricula. This should be especially easy for programs also complying with the Bologna Process.

Abstract: Intuitive and effective access to large volumes of information is increasingly important. As social media explodes as a useful source of information, so are methods required to access these large volumes of user-generated content. Word clouds are an effective information access tool. However, those generated over social media data often depict redundant and mis-ranked entries. This limits the users ’ ability to browse and explore datasets. This paper proposes a method for improving word cloud generation over social streams. Named entity expressions in tweets are detected, disambiguated and aggregated into entity clusters. A word cloud is generated from terms that represent the most relevant entity clusters. We find that word clouds with grouped named entities attain significantly broader coverage and significantly decreased content duplication. Further, access to relevant entries in the collection is improved. An extrinsic crowdsourced user evaluation of generated word clouds was performed. Word clouds with grouped named entities are rated as significantly more relevant and more diverse with respect to the baseline. In addition, we found that word clouds with higher levels of Mean Average Precision (MAP) are more likely to be rated by users as being relevant to the concepts reflected. Critically, this supports MAP as a tool for predicting word cloud quality without requiring a human in the loop. 1

Maximizing the spread and influence of the messages being published is a challenge for many social network users. Selecting the right content according to the information context and the user characteristics is essential for achieving this goal. We propose a model to automatically choose which information to publish on social networks given a set of possible messages. This model will tend to maximize the spread of the published message for a specific audience. The algorithm is based on the use of a contextual bandit model treating each new potential message as an arm to be selected. We conduct experiments on a Twitter dataset, comparing different algorithms and exploring the influence of the content and the characteristics of the messages on the information spread. The results demonstrate the model's ability to maximize the published information flow as well as it's ability to adapt its behavior to each particular audience.

The current boom of the Web is associated with the revenues originated from Web advertising. As one prevalent type of Web advertising, contextual advertising refers to the placement of the most relevant commercial textual ads within the content of a Web page, so as to provide a better user experience and thereby increase the revenues of Web site owners and an advertising platform. Therefore, in contextual advertising, the relevance of selected ads with a Web page is essential. However, some problems, such as homonymy and polysemy, low intersection of keywords and context mismatch, can lead to the selection of irrelevant textual ads for a Web page, making that a simple keyword matching technique generally gives poor accuracy. To overcome these problems and thus to improve the relevance of contextual ads, in this paper we propose a novel Wikipedia-based matching technique which, using selective matching strategies, selects a certain amount of relevant articles from Wikipedia as an intermediate semantic reference model for matching Web pages and textual ads. We call this technique SIWI: Selective Wikipedia Matching, which, instead of using the whole Wikipedia articles, only matches the most relevant articles for a page (or a textual ad), resulting in the effective improvement of the overall matching performance. An experimental evaluation is conducted, which runs over a set of real textual ads, a set of Web pages from the Internet and a dataset of more than 260 000 articles from Wikipedia. The experimental results show that our method performs better than existing matching strategies, which can deal with the matching over the large dataset of Wikipedia articles efficiently, and achieve a satisfactory contextual advertising effect.

Collaborative tagging services provided by various social web sites become popular means to mark web resources for different purposes such as categorization, expression of a preference and so on. However, the tags are of syntactic nature, in a free style and do not reflect semantics, resulting in the problems of redundancy, ambiguity and less semantics. Current tag-based recommender systems mainly take the explicit structural information among users, resources and tags into consideration, while neglecting the important implicit semantic relationships hidden in tagging data. In this study, we propose a Semantic Enhancement Recommendation strategy (SemRec), based on both structural information and semantic information through a unified fusion model. Extensive experiments conducted on two real datasets demonstarte the effectiveness of our approaches.

The amount of social media data dealing with medical and health issues increased significantly in the last couple of years. Medical social media data now provides a new source of information within information gaining contexts. Facts, experiences, opinions or information on behavior can be found in the Medicine 2.0 or Health 2.0 and could support a broad range of applications. This workshop is devoted to the technologies for dealing with social- and multi media for medical information gathering and exchange. This specific data and the processes of information gathering poses many challenges given the increasing content on the Web and the trade off of filtering noise at the cost of losing information which is potentially relevant.

Collaborative tagging has emerged as a useful means to organize and share resources on the Web. Recommender systems have been utilized tags for identifying similar resources and generate personalized recommendations. In this paper, we analyze social and behavioral aspects of a tag-based recommender system which suggests similar Web pages based on the similarity of their tags. Tagging behavior and language anomalies in tagging activities are some aspects examined from an experiment involving 38 people from 12 countries.

Business processes involve dynamic compositions of interleaved tasks. Therefore, ensuring reliable transactional processing of Web services is crucial for the success of Web service-based B2B and B2C applications. But the inherent autonomy and heterogeneity of Web services render the applicability of conventional ACID transaction models for Web services far from being straightforward. Current Web service transaction models relax the isolation property and rely on compensation mechanisms to ensure atomicity of business transactions in the presence of service failures. However, ensuring consistency in the open and dynamic environment of Web services, where interleaving business transactions enter and exit the system independently, remains an open issue. In this paper, we address this problem and propose an architecture that supports concurrency control on the Web services level. An extension to the standard framework for Web service transactions is proposed to enable detecting and handling transactional dependencies between concurrent business transactions. We also present an optimistic protocol for concurrency control that can be deployed in a fully distributed fashion within the proposed architecture. We also empirically evaluate the performance of the proposed solutions in terms of throughput and response time.

This paper provides an overview on the synergies between social web and knowledge managemen, topics, program committee members as well as summary of accepted papers for the SWKM2008 workshop.

In this article, we describe a Smart Space for Learning™ (SS4L) framework and infrastructure that enables personalized access to distributed heterogeneous knowledge repositories. Helping a learner to choose an appropriate learning resource or activity is a key problem which we address in this framework, enabling personalized access to federated learning repositories with a vast number of learning offers. Our infrastructure includes personalization strategies both at the query and the query results level. Query rewriting is based on learning and language preferences; rule-based and ranking-based personalization improves these results further. Rule-based reasoning techniques are supported by formal ontologies we have developed based on standard information models for learning domains; ranking-based recommendations are supported through ensuring minimal sets of predicates appearing in query results. Our evaluation studies show that the implemented solution enables learners to find relevant learning resources in a distributed environment and through goal-based personalization improves relevancy of results.

Business to business integration has recently been performed by employing Web service environments. Moreover, such environments are being provided by major players on the technology markets. Those environments are based on open specifications for transaction coordination. When a failure in such an environment occurs, a compensation can be initiated to recover from the failure. However, current environments have only limited capabilities for compensations, and are usually based on backward recovery. In this article, we introduce an environment to deal with advanced compensations based on forward recovery principles. We extend the existing Web service transaction coordination architecture and infrastructure in order to support flexible compensation operations. We use a contract-based approach, which allows the specification of permitted compensations at runtime. We introduce abstract service and adapter components, which allow us to separate the compensation logic from the coordination logic. In this way, we can easily plug in or plug out different compensation strategies based on a specification language defined on top of basic compensation activities and complex compensation types. Experiments with our approach and environment show that such an approach to compensation is feasible and beneficial. Additionally, we introduce a cost-benefit model to evaluate the proposed environment based on net value analysis. The evaluation shows in which circumstances the environment is economical.

This case study summarizes the demonstration of a semantic network of interoperable educational systems referred to as Smart Space for Learningtrade. We started connecting several educational nodes in projects such as Elena, Prolearn, and Icamp. Integration was achieved by using the interaction standard SQI, common schemas for querying and results presentation, and query exchange language, e.g. QEL. The paper particularly focuses on how heterogeneous nodes can be made interoperable by reusing generalizations of mediating components - building blocks for a Smart Space for Learningtrade