Publikationen

Busy lifestyles, abundant options, lack of knowledge ... there are many reasons why people make poor decisions relating to their health. Yet these poor decisions are leading to epidemics, which represent some of the greatest challenges we face as a society today. Noncommunicable Diseases (NCDs), which include cardiovascular diseases, cancer, chronic respiratory diseases and diabetes, account for ∼60% of total deaths worldwide. These diseases share the same four behavioural risk factors: tobacco use, unhealthy diet, physical inactivity and harmful consumption of alcohol and can be prevented and sometimes even reversed with simple lifestyle changes. Eating more healthily, exercising more appropriately, sleeping and relaxing more, as well as simply being more aware of one’s state of health are all things that would lead to improved health. Yet knowing exactly what to change and how, implementing changes and maintaining changes over long time periods are all things people find challenging. These are also problems, for which we believe recommender systems can provide assistance by offering specific, tailored suggestions for behavioural change. In recent years recommender systems for health has become a popular topic within the RecSys community and a selection of empirical contributions and demo systems have been published. Efforts to date, however have been sporadic and lack coordination. We lack shared infrastructure such as datasets, appropriate cross-disciplinary knowledge, even agreed upon goals. It is our aim to use this workshop as a vehicle to:

For the 7h International Workshop on Modeling Social Media, we aim to attract researchers from all over the world working in the field of behavioral analytics using web and social media data. Behavioral analytics is an important topic, e.g., concerning web applications as well as extensions in mobile and ubiquitous applications, for understanding user behavior. We would also like to invite researchers in the data and web mining community to lend their expertise to help to increase our understanding of the web and social media.

Recent research has unveiled the importance of online social networks for improving the quality of recommender systems and encouraged the research community to investigate better ways of exploiting the social information for recommendations. To contribute to this sparse field of research, in this paper we exploit users’ interactions along three data sources (marketplace, social network and location-based) to assess their performance in a barely studied domain: recommending products and domains of interests (i.e., product categories) to people in an online marketplace environment. To that end we defined sets of content- and network-based user similarity features for each data source and studied them isolated using an user-based Collaborative Filtering (CF) approach and in combination via a hybrid recommender algorithm, to assess which one provides the best recommendation performance. Interestingly, in our experiments conducted on a rich dataset collected from SecondLife, a popular online virtual world, we found that recommenders relying on user similarity features obtained from the social network data clearly yielded the best results in terms of accuracy in case of predicting products, whereas the features obtained from the marketplace and location-based data sources also obtained very good results in case of predicting categories. This finding indicates that all three types of data sources are important and should be taken into account depending on the level of specialization of the recommendation task.

We assume that recommender systems are more successful,when they are based on a thorough understanding of how people processinformation. In the current paper we test this assumption in the contextof social tagging systems. Cognitive research on how people assign tagshas shown that they draw on two interconnected levels of knowledge intheir memory: on a conceptual level of semantic fields or LDA topics,and on a lexical level that turns patterns on the semantic level intowords. Another strand of tagging research reveals a strong impact oftime-dependent forgetting on users' tag choices, such that recently usedtags have a higher probability being reused than "older" tags. In thispaper, we align both strands by implementing a computational theory ofhuman memory that integrates the two-level conception and the processof forgetting in form of a tag recommender. Furthermore, we test theapproach in three large-scale social tagging datasets that are drawn fromBibSonomy, CiteULike and Flickr.As expected, our results reveal a selective effect of time: forgetting ismuch more pronounced on the lexical level of tags. Second, an extensiveevaluation based on this observation shows that a tag recommender interconnectingthe semantic and lexical level based on a theory of humancategorization and integrating time-dependent forgetting on the lexicallevel results in high accuracy predictions and outperforms other wellestablishedalgorithms, such as Collaborative Filtering, Pairwise InteractionTensor Factorization, FolkRank and two alternative time-dependentapproaches. We conclude that tag recommenders will benefit from goingbeyond the manifest level of word co-occurrences, and from includingforgetting processes on the lexical level.

In this paper, we introduce a tag recommendation algorithmthat mimics the way humans draw on items in their long-term memory.Based on a theory of human memory, the approach estimates a tag'sprobability being applied by a particular user as a function of usagefrequency and recency of the tag in the user's past. This probability isfurther refined by considering the inuence of the current semantic contextof the user's tagging situation. Using three real-world folksonomiesgathered from bookmarks in BibSonomy, CiteULike and Flickr, we showhow refining frequency-based estimates by considering usage recency andcontextual inuence outperforms conventional "most popular tags" approachesand another existing and very effective but less theory-driven,time-dependent recommendation mechanism.By combining our approach with a simple resource-specific frequencyanalysis, our algorithm outperforms other well-established algorithms,such as FolkRank, Pairwise Interaction Tensor Factorization and CollaborativeFiltering. We conclude that our approach provides an accurateand computationally efficient model of a user's temporal tagging behavior.We demonstrate how effective principles of recommender systemscan be designed and implemented if human memory processes are takeninto account.