Dominik Kowald

Armin Haberl, Jürgen Fleiß, Dominik Kowald et al.

aTrain is an open-source and offline tool for transcribing audio data in multiple languages with CPU and NVIDIA GPU support. It is specifically designed for researchers using qualitative data generated from various forms of speech interactions with research participants. aTrain requires no programming skills, runs on most computers, does not require an internet connection, and was verified not to upload data to any server. aTrain combines OpenAI's Whisper model with speaker recognition to provide output that integrates with the popular qualitative data analysis software tools MAXQDA and ATLAS.ti. It has an easy-to-use graphical interface and is provided as a Windows-App through the Microsoft Store allowing for simple installation by researchers. The source code is freely available on GitHub. Having developed aTrain with a focus on speed on local computers, we show that the transcription time on current mobile CPUs is around 2 to 3 times the duration of the audio file using the highest-accuracy transcription models. If an entry-level graphics card is available, the transcription speed increases to 20% of the audio duration.

Dominik Kowald, Gregor Mayr, Markus Schedl et al.

Recent research has suggested different metrics to measure the inconsistency of recommendation performance, including the accuracy difference between user groups, miscalibration, and popularity lift. However, a study that relates miscalibration and popularity lift to recommendation accuracy across different user groups is still missing. Additionally, it is unclear if particular genres contribute to the emergence of inconsistency in recommendation performance across user groups. In this paper, we present an analysis of these three aspects of five well-known recommendation algorithms for user groups that differ in their preference for popular content. Additionally, we study how different genres affect the inconsistency of recommendation performance, and how this is aligned with the popularity of the genres. Using data from LastFm, MovieLens, and MyAnimeList, we present two key findings. First, we find that users with little interest in popular content receive the worst recommendation accuracy, and that this is aligned with miscalibration and popularity lift. Second, our experiments show that particular genres contribute to a different extent to the inconsistency of recommendation performance, especially in terms of miscalibration in the case of the MyAnimeList dataset.

Harald Semmelrock, Simone Kopeinik, Dieter Theiler et al.

Research is facing a reproducibility crisis, in which the results and findings of many studies are difficult or even impossible to reproduce. This is also the case in machine learning (ML) and artificial intelligence (AI) research. Often, this is the case due to unpublished data and/or source-code, and due to sensitivity to ML training conditions. Although different solutions to address this issue are discussed in the research community such as using ML platforms, the level of reproducibility in ML-driven research is not increasing substantially. Therefore, in this mini survey, we review the literature on reproducibility in ML-driven research with three main aims: (i) reflect on the current situation of ML reproducibility in various research fields, (ii) identify reproducibility issues and barriers that exist in these research fields applying ML, and (iii) identify potential drivers such as tools, practices, and interventions that support ML reproducibility. With this, we hope to contribute to decisions on the viability of different solutions for supporting ML reproducibility.

Dominik Kowald, Emanuel Lacic

Multimedia recommender systems suggest media items, e.g., songs, (digital) books and movies, to users by utilizing concepts of traditional recommender systems such as collaborative filtering. In this paper, we investigate a potential issue of such collaborative-filtering based multimedia recommender systems, namely popularity bias that leads to the underrepresentation of unpopular items in the recommendation lists. Therefore, we study four multimedia datasets, i.e., LastFm, MovieLens, BookCrossing and MyAnimeList, that we each split into three user groups differing in their inclination to popularity, i.e., LowPop, MedPop and HighPop. Using these user groups, we evaluate four collaborative filtering-based algorithms with respect to popularity bias on the item and the user level. Our findings are three-fold: firstly, we show that users with little interest into popular items tend to have large user profiles and thus, are important data sources for multimedia recommender systems. Secondly, we find that popular items are recommended more frequently than unpopular ones. Thirdly, we find that users with little interest into popular items receive significantly worse recommendations than users with medium or high interest into popularity.

Sebastian Scher, Simone Kopeinik, Andreas Trügler et al.

The use of data-driven decision support by public agencies is becoming more widespread and already influences the allocation of public resources. This raises ethical concerns, as it has adversely affected minorities and historically discriminated groups. In this paper, we use an approach that combines statistics and data-driven approaches with dynamical modeling to assess long-term fairness effects of labor market interventions. Specifically, we develop and use a model to investigate the impact of decisions caused by a public employment authority that selectively supports job-seekers through targeted help. The selection of who receives what help is based on a data-driven intervention model that estimates an individual's chances of finding a job in a timely manner and rests upon data that describes a population in which skills relevant to the labor market are unevenly distributed between two groups (e.g., males and females). The intervention model has incomplete access to the individual's actual skills and can augment this with knowledge of the individual's group affiliation, thus using a protected attribute to increase predictive accuracy. We assess this intervention model's dynamics -- especially fairness-related issues and trade-offs between different fairness goals -- over time and compare it to an intervention model that does not use group affiliation as a predictive feature. We conclude that in order to quantify the trade-off correctly and to assess the long-term fairness effects of such a system in the real-world, careful modeling of the surrounding labor market is indispensable.

Sebastian Scher, Bernhard Geiger, Simone Kopeinik et al.

For a long time, machine learning (ML) has been seen as the abstract problem of learning relationships from data independent of the surrounding settings. This has recently been challenged, and methods have been proposed to include external constraints in the machine learning models. These methods usually come from application-specific fields, such as de-biasing algorithms in the field of fairness in ML or physical constraints in the fields of physics and engineering. In this paper, we present and discuss a conceptual high-level model that unifies these approaches in a common language. We hope that this will enable and foster exchange between the different fields and their different methods for including external constraints into ML models, and thus leaving purely data-centric approaches.

Dominik Kowald, Simone Kopeinik, Elisabeth Lex

Recommender systems have become important tools to support users in identifying relevant content in an overloaded information space. To ease the development of recommender systems, a number of recommender frameworks have been proposed that serve a wide range of application domains. Our TagRec framework is one of the few examples of an open-source framework tailored towards developing and evaluating tag-based recommender systems. In this paper, we present the current, updated state of TagRec, and we summarize and reflect on four use cases that have been implemented with TagRec: (i) tag recommendations, (ii) resource recommendations, (iii) recommendation evaluation, and (iv) hashtag recommendations. To date, TagRec served the development and/or evaluation process of tag-based recommender systems in two large scale European research projects, which have been described in 17 research papers. Thus, we believe that this work is of interest for both researchers and practitioners of tag-based recommender systems.

Florian Atzenhofer-Baumgartner, Dominik Kowald

User models for recommender systems (RecSys) typically assume stable preferences, similarity-based relevance, and session-bounded interactions -- assumptions derived from high-volume consumer contexts. This paper investigates these assumptions for humanities scholars working with digital archives. Following a human-centered design approach, we conducted focus groups and analyzed interview data from 18 researchers. Our analysis identifies four dimensions where scholarly information-seeking diverges from common RecSys user modeling: (1) context volatility -- preferences shift with research tasks and domain expertise; (2) epistemic trust -- relevance depends on verifiable provenance; (3) contrastive seeking -- researchers seek items that challenge their current direction; and (4) strand continuity -- research spans long-term threads rather than discrete sessions. We discuss implications for user modeling and outline how these dimensions relate to collaborative filtering, content-based, and session-based recommendation. We propose these dimensions as a diagnostic framework applicable beyond archives to similar application domains where typical user modeling assumptions may not hold.

Andrea Forster, Peter Müllner, Denis Helic et al.

LLM agents are increasingly used for personalization due to their ability to communicate directly with users in natural language, integrate external knowledge bases, and negotiate with other (possibly human) agents. Especially in multistakeholder AI systems with multiple distinct objectives, LLM agents are used to independently optimize for each stakeholder's goals. Here, stakeholder alignment is essential to identify and map these goals to provide LLM agents with quantifiable objectives. Plus, the way in which the outputs of the LLM agents are aggregated is fundamental to ensuring fair outcomes for all agents and, therefore, stakeholders. In this work, we identify open research challenges and propose a conceptual framework for designing fair multi-agent multistakeholder personalization systems that balance competing stakeholder objectives. Our framework integrates (i) methods to align stakeholder objectives and LLM agents, (ii) aggregation strategies, e.g., based on social choice theory, to form fair collective decisions, and (iii) stakeholder-centric evaluation procedures for both individual and collective agent behavior. We showcase our framework through a tourism use case and discuss possible applications in other domains, such as education and healthcare. Finally, we discuss domain-specific fairness tensions and review datasets for evaluating multistakeholder fairness and multi-agent personalization systems.

Dominik Kowald, Sebastian Scher, Viktoria Pammer-Schindler et al.

Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a result, there has been a surge in public and academic discussions about aspects that AI systems must fulfill to be considered trustworthy. In this paper, we synthesize existing conceptualizations of trustworthy AI along six requirements: 1) human agency and oversight, 2) fairness and non-discrimination, 3) transparency and explainability, 4) robustness and accuracy, 5) privacy and security, and 6) accountability. For each one, we provide a definition, describe how it can be established and evaluated, and discuss requirement-specific research challenges. Finally, we conclude this analysis by identifying overarching research challenges across the requirements with respect to 1) interdisciplinary research, 2) conceptual clarity, 3) context-dependency, 4) dynamics in evolving systems, and 5) investigations in real-world contexts. Thus, this paper synthesizes and consolidates a wide-ranging and active discussion currently taking place in various academic sub-communities and public forums. It aims to serve as a reference for a broad audience and as a basis for future research directions.

Peter Müllner, Dominik Kowald, Markus Schedl et al.

Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the data level, we apply DP only to the most stereotypical user data likely to reveal sensitive attributes, such as gender or age, to reduce unnecessary perturbation; we refer to this as targeted DP. At the model level, we use meta-learning to improve robustness to remaining DP-noise. This achieves a better trade-off between accuracy and privacy than standard approaches: Meta-learning improves accuracy and targeted DP leads to lower empirical privacy risk compared to uniformly applied DP and full DP baselines. Overall, our findings show that selectively applying DP at the data level together with meta-learning at the model level can effectively balance recommendation accuracy and user privacy.

Robin Burke, Gediminas Adomavicius, Toine Bogers et al.

Multistakeholder recommender systems are those that account for the impacts and preferences of multiple groups of individuals, not just the end users receiving recommendations. Due to their complexity, these systems cannot be evaluated strictly by the overall utility of a single stakeholder, as is often the case of more mainstream recommender system applications. In this article, we focus our discussion on the challenges of multistakeholder evaluation of recommender systems. We bring attention to the different aspects involved -- from the range of stakeholders involved (including but not limited to providers and consumers) to the values and specific goals of each relevant stakeholder. We discuss how to move from theoretical principles to practical implementation, providing specific use case examples. Finally, we outline open research directions for the RecSys community to explore. We aim to provide guidance to researchers and practitioners about incorporating these complex and domain-dependent issues of evaluation in the course of designing, developing, and researching applications with multistakeholder aspects.

Lea Demelius, Dominik Kowald, Simone Kopeinik et al.

Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning dynamics and, consequently, its output. This can affect the model's performance and fairness. While the majority of studies on the topic report a negative impact on fairness, it has recently been suggested that fairness levels comparable to non-private models can be achieved by optimizing hyperparameters for performance directly on differentially private models (rather than re-using hyperparameters from non-private models, as is common practice). In this work, we analyze the generalizability of this claim by 1) comparing the disparate impact of DPSGD on different performance metrics, and 2) analyzing it over a wide range of hyperparameter settings. We highlight that a disparate impact on one metric does not necessarily imply a disparate impact on another. Most importantly, we show that while optimizing hyperparameters directly on differentially private models does not mitigate the disparate impact of DPSGD reliably, it can still lead to improved utility-fairness trade-offs compared to re-using hyperparameters from non-private models. We stress, however, that any form of hyperparameter tuning entails additional privacy leakage, calling for careful considerations of how to balance privacy, utility and fairness. Finally, we extend our analyses to DPSGD-Global-Adapt, a variant of DPSGD designed to mitigate the disparate impact on accuracy, and conclude that this alternative may not be a robust solution with respect to hyperparameter choice.

Gregor Autischer, Kerstin Waxnegger, Dominik Kowald

In this work-in-progress, we investigate the certification of AI systems, focusing on the practical application and limitations of existing certification catalogues in the light of the AI Act by attempting to certify a publicly available AI system. We aim to evaluate how well current approaches work to effectively certify an AI system, and how publicly accessible AI systems, that might not be actively maintained or initially intended for certification, can be selected and used for a sample certification process. Our methodology involves leveraging the Fraunhofer AI Assessment Catalogue as a comprehensive tool to systematically assess an AI model's compliance with certification standards. We find that while the catalogue effectively structures the evaluation process, it can also be cumbersome and time-consuming to use. We observe the limitations of an AI system that has no active development team anymore and highlighted the importance of complete system documentation. Finally, we identify some limitations of the certification catalogues used and proposed ideas on how to streamline the certification process.

Harald Semmelrock, Tony Ross-Hellauer, Simone Kopeinik et al.

Many research fields are currently reckoning with issues of poor levels of reproducibility. Some label it a "crisis", and research employing or building Machine Learning (ML) models is no exception. Issues including lack of transparency, data or code, poor adherence to standards, and the sensitivity of ML training conditions mean that many papers are not even reproducible in principle. Where they are, though, reproducibility experiments have found worryingly low degrees of similarity with original results. Despite previous appeals from ML researchers on this topic and various initiatives from conference reproducibility tracks to the ACM's new Emerging Interest Group on Reproducibility and Replicability, we contend that the general community continues to take this issue too lightly. Poor reproducibility threatens trust in and integrity of research results. Therefore, in this article, we lay out a new perspective on the key barriers and drivers (both procedural and technical) to increased reproducibility at various levels (methods, code, data, and experiments). We then map the drivers to the barriers to give concrete advice for strategies for researchers to mitigate reproducibility issues in their own work, to lay out key areas where further research is needed in specific areas, and to further ignite discussion on the threat presented by these urgent issues.

Emanuel Lacic, Leon Fadljevic, Franz Weissenboeck et al.

Personalized news recommender systems support readers in finding the right and relevant articles in online news platforms. In this paper, we discuss the introduction of personalized, content-based news recommendations on DiePresse, a popular Austrian online news platform, focusing on two specific aspects: (i) user interface type, and (ii) popularity bias mitigation. Therefore, we conducted a two-weeks online study that started in October 2020, in which we analyzed the impact of recommendations on two user groups, i.e., anonymous and subscribed users, and three user interface types, i.e., on a desktop, mobile and tablet device. With respect to user interface types, we find that the probability of a recommendation to be seen is the highest for desktop devices, while the probability of interacting with recommendations is the highest for mobile devices. With respect to popularity bias mitigation, we find that personalized, content-based news recommendations can lead to a more balanced distribution of news articles' readership popularity in the case of anonymous users. Apart from that, we find that significant events (e.g., the COVID-19 lockdown announcement in Austria and the Vienna terror attack) influence the general consumption behavior of popular articles for both, anonymous and subscribed users.

Peter Müllner, Elisabeth Lex, Dominik Kowald

In this position paper, we discuss the merits of simulating privacy dynamics in recommender systems. We study this issue at hand from two perspectives: Firstly, we present a conceptual approach to integrate privacy into recommender system simulations, whose key elements are privacy agents. These agents can enhance users' profiles with different privacy preferences, e.g., their inclination to disclose data to the recommender system. Plus, they can protect users' privacy by guarding all actions that could be a threat to privacy. For example, agents can prohibit a user's privacy-threatening actions or apply privacy-enhancing techniques, e.g., Differential Privacy, to make actions less threatening. Secondly, we identify three critical topics for future research in privacy-aware recommender system simulations: (i) How could we model users' privacy preferences and protect users from performing any privacy-threatening actions? (ii) To what extent do privacy agents modify the users' document preferences? (iii) How do privacy preferences and privacy protections impact recommendations and privacy of others? Our conceptual privacy-aware simulation approach makes it possible to investigate the impact of privacy preferences and privacy protection on the micro-level, i.e., a single user, but also on the macro-level, i.e., all recommender system users. With this work, we hope to present perspectives on how privacy-aware simulations could be realized, such that they enable researchers to study the dynamics of privacy within a recommender system.

Oleg Lesota, Alessandro B. Melchiorre, Navid Rekabsaz et al.

Several studies have identified discrepancies between the popularity of items in user profiles and the corresponding recommendation lists. Such behavior, which concerns a variety of recommendation algorithms, is referred to as popularity bias. Existing work predominantly adopts simple statistical measures, such as the difference of mean or median popularity, to quantify popularity bias. Moreover, it does so irrespective of user characteristics other than the inclination to popular content. In this work, in contrast, we propose to investigate popularity differences (between the user profile and recommendation list) in terms of median, a variety of statistical moments, as well as similarity measures that consider the entire popularity distributions (Kullback-Leibler divergence and Kendall's tau rank-order correlation). This results in a more detailed picture of the characteristics of popularity bias. Furthermore, we investigate whether such algorithmic popularity bias affects users of different genders in the same way. We focus on music recommendation and conduct experiments on the recently released standardized LFM-2b dataset, containing listening profiles of Last.fm users. We investigate the algorithmic popularity bias of seven common recommendation algorithms (five collaborative filtering and two baselines). Our experiments show that (1) the studied metrics provide novel insights into popularity bias in comparison with only using average differences, (2) algorithms less inclined towards popularity bias amplification do not necessarily perform worse in terms of utility (NDCG), (3) the majority of the investigated recommenders intensify the popularity bias of the female users.

Dominik Kowald, Peter Muellner, Eva Zangerle et al.

Music recommender systems have become an integral part of music streaming services such as Spotify and Last.fm to assist users navigating the extensive music collections offered by them. However, while music listeners interested in mainstream music are traditionally served well by music recommender systems, users interested in music beyond the mainstream (i.e., non-popular music) rarely receive relevant recommendations. In this paper, we study the characteristics of beyond-mainstream music and music listeners and analyze to what extent these characteristics impact the quality of music recommendations provided. Therefore, we create a novel dataset consisting of Last.fm listening histories of several thousand beyond-mainstream music listeners, which we enrich with additional metadata describing music tracks and music listeners. Our analysis of this dataset shows four subgroups within the group of beyond-mainstream music listeners that differ not only with respect to their preferred music but also with their demographic characteristics. Furthermore, we evaluate the quality of music recommendations that these subgroups are provided with four different recommendation algorithms where we find significant differences between the groups. Specifically, our results show a positive correlation between a subgroup's openness towards music listened to by members of other subgroups and recommendation accuracy. We believe that our findings provide valuable insights for developing improved user models and recommendation approaches to better serve beyond-mainstream music listeners.

Peter Müllner, Dominik Kowald, Elisabeth Lex

In this paper, we explore the reproducibility of MetaMF, a meta matrix factorization framework introduced by Lin et al. MetaMF employs meta learning for federated rating prediction to preserve users' privacy. We reproduce the experiments of Lin et al. on five datasets, i.e., Douban, Hetrec-MovieLens, MovieLens 1M, Ciao, and Jester. Also, we study the impact of meta learning on the accuracy of MetaMF's recommendations. Furthermore, in our work, we acknowledge that users may have different tolerances for revealing information about themselves. Hence, in a second strand of experiments, we investigate the robustness of MetaMF against strict privacy constraints. Our study illustrates that we can reproduce most of Lin et al.'s results. Plus, we provide strong evidence that meta learning is essential for MetaMF's robustness against strict privacy constraints.

Markus Schedl, Christine Bauer, Wolfgang Reisinger et al.

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the "music mainstream" strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervised learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user's country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-a-vis state-of-the-art algorithms that do not exploit this type of context information.

Tomislav Duricic, Hussain Hussain, Emanuel Lacic et al.

In this work, we study the utility of graph embeddings to generate latent user representations for trust-based collaborative filtering. In a cold-start setting, on three publicly available datasets, we evaluate approaches from four method families: (i) factorization-based, (ii) random walk-based, (iii) deep learning-based, and (iv) the Large-scale Information Network Embedding (LINE) approach. We find that across the four families, random-walk-based approaches consistently achieve the best accuracy. Besides, they result in highly novel and diverse recommendations. Furthermore, our results show that the use of graph embeddings in trust-based collaborative filtering significantly improves user coverage.

Dominik Kowald, Elisabeth Lex, Markus Schedl

In this paper, we introduce a psychology-inspired approach to model and predict the music genre preferences of different groups of users by utilizing human memory processes. These processes describe how humans access information units in their memory by considering the factors of (i) past usage frequency, (ii) past usage recency, and (iii) the current context. Using a publicly available dataset of more than a billion music listening records shared on the music streaming platform Last.fm, we find that our approach provides significantly better prediction accuracy results than various baseline algorithms for all evaluated user groups, i.e., (i) low-mainstream music listeners, (ii) medium-mainstream music listeners, and (iii) high-mainstream music listeners. Furthermore, our approach is based on a simple psychological model, which contributes to the transparency and explainability of the calculated predictions.

Dominik Kowald, Markus Schedl, Elisabeth Lex

Research has shown that recommender systems are typically biased towards popular items, which leads to less popular items being underrepresented in recommendations. The recent work of Abdollahpouri et al. in the context of movie recommendations has shown that this popularity bias leads to unfair treatment of both long-tail items as well as users with little interest in popular items. In this paper, we reproduce the analyses of Abdollahpouri et al. in the context of music recommendation. Specifically, we investigate three user groups from the LastFM music platform that are categorized based on how much their listening preferences deviate from the most popular music among all LastFM users in the dataset: (i) low-mainstream users, (ii) medium-mainstream users, and (iii) high-mainstream users. In line with Abdollahpouri et al., we find that state-of-the-art recommendation algorithms favor popular items also in the music domain. However, their proposed Group Average Popularity metric yields different results for LastFM than for the movie domain, presumably due to the larger number of available items (i.e., music artists) in the LastFM dataset we use. Finally, we compare the accuracy results of the recommendation algorithms for the three user groups and find that the low-mainstreaminess group significantly receives the worst recommendations.

Emanuel Lacic, Dominik Kowald, Dieter Theiler et al.

In this paper, we present our work to support publishers and editors in finding descriptive tags for e-books through tag recommendations. We propose a hybrid tag recommendation system for e-books, which leverages search query terms from Amazon users and e-book metadata, which is assigned by publishers and editors. Our idea is to mimic the vocabulary of users in Amazon, who search for and review e-books, and to combine these search terms with editor tags in a hybrid tag recommendation approach. In total, we evaluate 19 tag recommendation algorithms on the review content of Amazon users, which reflects the readers' vocabulary. Our results show that we can improve the performance of tag recommender systems for e-books both concerning tag recommendation accuracy, diversity as well as a novel semantic similarity metric, which we also propose in this paper.

Dominik Kowald, Matthias Traub, Dieter Theiler et al.

This work addresses the problem of providing and evaluating recommendations in data markets. Since most of the research in recommender systems is focused on the bipartite relationship between users and items (e.g., movies), we extend this view to the tripartite relationship between users, datasets and services, which is present in data markets. Between these entities, we identify four use cases for recommendations: (i) recommendation of datasets for users, (ii) recommendation of services for users, (iii) recommendation of services for datasets, and (iv) recommendation of datasets for services. Using the open Meta Kaggle dataset, we evaluate the recommendation accuracy of a popularity-based as well as a collaborative filtering-based algorithm for these four use cases and find that the recommendation accuracy strongly depends on the given use case. The presented work contributes to the tripartite recommendation problem in general and to the under-researched portfolio of evaluating recommender systems for data markets in particular.

Elisabeth Lex, Dominik Kowald

In our work [KPL17], we study temporal usage patterns of Twitter hashtags, and we use the Base-Level Learning (BLL) equation from the cognitive architecture ACT-R [An04] to model how a person reuses her own, individual hashtags as well as hashtags from her social network. The BLL equation accounts for the time-dependent decay of item exposure in human memory. According to BLL, the usefulness of a piece of information (e.g., a hashtag) is defined by how frequently and how recently it was used in the past, following a time-dependent decay that is best modeled with a power-law distribution. We used the BLL equation in our previous work to recommend tags in social bookmarking systems [KL16]. Here [KPL17], we adopt the BLL equation to model temporal reuse patterns of individual (i.e., reusing own hashtags) and social hashtags (i.e., reusing hashtags, which has been previously used by a followee) and to build a cognitive-inspired hashtag recommendation algorithm. We demonstrate the efficacy of our approach in two empirical social networks crawled from Twitter, i.e., CompSci and Random (for details about the datasets, see [KPL17]). Our results show that our approach can outperform current state-of-the-art hashtag recommendation approaches.

Dominik Kowald, Elisabeth Lex, Markus Schedl

Music recommender systems have become central parts of popular streaming platforms such as Last.fm, Pandora, or Spotify to help users find music that fits their preferences. These systems learn from the past listening events of users to recommend music a user will likely listen to in the future. Here, current algorithms typically employ collaborative filtering (CF) utilizing similarities between users' listening behaviors. Some approaches also combine CF with content features into hybrid recommender systems. While music recommender systems can provide quality recommendations to listeners of mainstream music artists, recent research has shown that they tend to discriminate listeners of unorthodox, low-mainstream artists. This is foremost due to the scarcity of usage data of low-mainstream music as music consumption patterns are biased towards popular artists. Thus, the objective of our work is to provide a novel approach for modeling artist preferences of users with different music consumption patterns and listening habits.

Tomislav Duricic, Emanuel Lacic, Dominik Kowald et al.

User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items. One solution is to incorporate additional information into the recommendation process such as explicit trust scores that are assigned by users to others or implicit trust relationships that result from social connections between users. Such relationships typically form a very sparse trust network, which can be utilized to generate recommendations for users based on people they trust. In our work, we explore the use of regular equivalence applied to a trust network to generate a similarity matrix that is used for selecting k-nearest neighbors used for item recommendation. Two vertices in a network are regularly equivalent if their neighbors are themselves equivalent and by using the iterative approach of calculating regular equivalence, we can study the impact of strong and weak ties on item recommendation. We evaluate our approach on cold-start users on a dataset crawled from Epinions and find that by using weak ties in addition to strong ties, we can improve the performance of a trust-based recommender in terms of recommendation accuracy.

Elisabeth Lex, Mario Wagner, Dominik Kowald

In this work, we propose a content-based recommendation approach to increase exposure to opposing beliefs and opinions. Our aim is to help provide users with more diverse viewpoints on issues, which are discussed in partisan groups from different perspectives. Since due to the backfire effect, people's original beliefs tend to strengthen when challenged with counter evidence, we need to expose them to opposing viewpoints at the right time. The preliminary work presented here describes our first step into this direction. As illustrative showcase, we take the political debate on Twitter around the presidency of Donald Trump.

Dominik Kowald, Elisabeth Lex

The micro-blogging platform Twitter allows its nearly 320 million monthly active users to build a network of follower connections to other Twitter users (i.e., followees) in order to subscribe to content posted by these users. With this feature, Twitter has become one of the most popular social networks on the Web and was also the first platform that offered the concept of hashtags. Hashtags are freely-chosen keywords, which start with the hash character, to annotate, categorize and contextualize Twitter posts (i.e., tweets). Although hashtags are widely accepted and used by the Twitter community, the heavy reuse of hashtags that are popular in the personal Twitter networks (i.e., own hashtags and hashtags used by followees) can lead to filter bubble effects and thus, to situations, in which only content associated with these hashtags are presented to the user. These filter bubble effects are also highly associated with the concept of confirmation bias, which is the tendency to favor and reuse information that confirms personal preferences. One example would be a Twitter user who is interested in political tweets of US president Donald Trump. Depending on the hashtags used, the user could either be stuck in a pro-Trump (e.g., #MAGA) or contra-Trump (e.g., #fakepresident) filter bubble. Therefore, the goal of this paper is to study confirmation bias and filter bubble effects in hashtag usage on Twitter by treating the reuse of hashtags as a phenomenon that fosters confirmation bias.

Emanuel Lacic, Dominik Kowald, Elisabeth Lex

In this paper, we present work-in-progress on applying user pre-filtering to speed up and enhance recommendations based on Collaborative Filtering. We propose to pre-filter users in order to extract a smaller set of candidate neighbors, who exhibit a high number of overlapping entities and to compute the final user similarities based on this set. To realize this, we exploit features of the high-performance search engine Apache Solr and integrate them into a scalable recommender system. We have evaluated our approach on a dataset gathered from Foursquare and our evaluation results suggest that our proposed user pre-filtering step can help to achieve both a better runtime performance as well as an increase in overall recommendation accuracy.

Dominik Kowald, Emanuel Lacic, Dieter Theiler et al.

In this paper, we present preliminary results of AFEL-REC, a recommender system for social learning environments. AFEL-REC is build upon a scalable software architecture to provide recommendations of learning resources in near real-time. Furthermore, AFEL-REC can cope with any kind of data that is present in social learning environments such as resource metadata, user interactions or social tags. We provide a preliminary evaluation of three recommendation use cases implemented in AFEL-REC and we find that utilizing social data in form of tags is helpful for not only improving recommendation accuracy but also coverage. This paper should be valuable for both researchers and practitioners interested in providing resource recommendations in social learning environments.

Tomislav Duricic, Emanuel Lacic, Dominik Kowald et al.

User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. This approach is based on finding the most relevant k users from whose rating history we can extract items to recommend. CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items. One solution is to incorporate additional information into the recommendation process such as explicit trust scores that are assigned by users to others or implicit trust relationships that result from social connections between users. Such relationships typically form a very sparse trust network, which can be utilized to generate recommendations for users based on people they trust. In our work, we explore the use of a measure from network science, i.e. regular equivalence, applied to a trust network to generate a similarity matrix that is used to select the k-nearest neighbors for recommending items. We evaluate our approach on Epinions and we find that we can outperform related methods for tackling cold-start users in terms of recommendation accuracy.

Dominik Kowald

With the emergence of Web 2.0, tag recommenders have become important tools, which aim to support users in finding descriptive tags for their bookmarked resources. Although current algorithms provide good results in terms of tag prediction accuracy, they are often designed in a data-driven way and thus, lack a thorough understanding of the cognitive processes that play a role when people assign tags to resources. This thesis aims at modeling these cognitive dynamics in social tagging in order to improve tag recommendations and to better understand the underlying processes. As a first attempt in this direction, we have implemented an interplay between individual micro-level (e.g., categorizing resources or temporal dynamics) and collective macro-level (e.g., imitating other users' tags) processes in the form of a novel tag recommender algorithm. The preliminary results for datasets gathered from BibSonomy, CiteULike and Delicious show that our proposed approach can outperform current state-of-the-art algorithms, such as Collaborative Filtering, FolkRank or Pairwise Interaction Tensor Factorization. We conclude that recommender systems can be improved by incorporating related principles of human cognition.

Dominik Kowald, Elisabeth Lex

In this paper, we study the imbalance between current state-of-the-art tag recommendation algorithms and the folksonomy structures of real-world social tagging systems. While algorithms such as FolkRank are designed for dense folksonomy structures, most social tagging systems exhibit a sparse nature. To overcome this imbalance, we show that cognitive-inspired algorithms, which model the tag vocabulary of a user in a cognitive-plausible way, can be helpful. Our present approach does this via implementing the activation equation of the cognitive architecture ACT-R, which determines the usefulness of units in human memory (e.g., tags). In this sense, our long-term research goal is to design hybrid recommendation approaches, which combine the advantages of both worlds in order to adapt to the current setting (i.e., sparse vs. dense ones).

Dominik Kowald

This thesis was submitted by Dr. Dominik Kowald to the Institute of Interactive Systems and Data Science of Graz University of Technology in Austria on the 5th of September 2017 for the attainment of the degree 'Dr.techn'. The supervisors of this thesis have been Prof. Stefanie Lindstaedt and Ass.Prof. Elisabeth Lex from Graz University of Technology, and the external assessor has been Prof. Tobias Ley from Tallinn University. In the current enthusiasm around Data Science and Big Data Analytics, it is important to mention that only theory-guided approaches will truly enable us to fully understand why an algorithm works and how specific results can be explained. It was the goal of this dissertation research to follow this path by demonstrating that a recommender system inspired by human memory theory can have a true impact in the field.

Dominik Kowald, Paul Seitlinger, Tobias Ley et al.

In this paper, we present the results of an online study with the aim to shed light on the impact that semantic context cues have on the user acceptance of tag recommendations. Therefore, we conducted a work-integrated social bookmarking scenario with 17 university employees in order to compare the user acceptance of a context-aware tag recommendation algorithm called 3Layers with the user acceptance of a simple popularity-based baseline. In this scenario, we validated and verified the hypothesis that semantic context cues have a higher impact on the user acceptance of tag recommendations in a collaborative tagging setting than in an individual tagging setting. With this paper, we contribute to the sparse line of research presenting online recommendation studies.

Emanuel Lacic, Dominik Kowald, Markus Reiter-Haas et al.

In this work, we address the problem of recommending jobs to university students. For this, we explore the utilization of neural item embeddings for the task of content-based recommendation, and we propose to integrate the factors of frequency and recency of interactions with job postings to combine these item embeddings. We evaluate our job recommendation system on a dataset of the Austrian student job portal Studo using prediction accuracy, diversity and an adapted novelty metric. This paper demonstrates that utilizing frequency and recency of interactions with job postings for combining item embeddings results in a robust model with respect to accuracy and diversity, which also provides the best adapted novelty results.

Dominik Kowald, Subhash Pujari, Elisabeth Lex

Hashtags have become a powerful tool in social platforms such as Twitter to categorize and search for content, and to spread short messages across members of the social network. In this paper, we study temporal hashtag usage practices in Twitter with the aim of designing a cognitive-inspired hashtag recommendation algorithm we call BLLi,s. Our main idea is to incorporate the effect of time on (i) individual hashtag reuse (i.e., reusing own hashtags), and (ii) social hashtag reuse (i.e., reusing hashtags, which has been previously used by a followee) into a predictive model. For this, we turn to the Base-Level Learning (BLL) equation from the cognitive architecture ACT-R, which accounts for the time-dependent decay of item exposure in human memory. We validate BLLi,s using two crawled Twitter datasets in two evaluation scenarios: firstly, only temporal usage patterns of past hashtag assignments are utilized and secondly, these patterns are combined with a content-based analysis of the current tweet. In both scenarios, we find not only that temporal effects play an important role for both individual and social hashtag reuse but also that BLLi,s provides significantly better prediction accuracy and ranking results than current state-of-the-art hashtag recommendation methods.

Emanuel Lacic, Dominik Kowald, Elisabeth Lex

Air travel is one of the most frequently used means of transportation in our every-day life. Thus, it is not surprising that an increasing number of travelers share their experiences with airlines and airports in form of online reviews on the Web. In this work, we thrive to explain and uncover the features of airline reviews that contribute most to traveler satisfaction. To that end, we examine reviews crawled from the Skytrax air travel review portal. Skytrax provides four review categories to review airports, lounges, airlines and seats. Each review category consists of several five-star ratings as well as free-text review content. In this paper, we conducted a comprehensive feature study and we find that not only five-star rating information such as airport queuing time and lounge comfort highly correlate with traveler satisfaction but also textual features in the form of the inferred review text sentiment. Based on our findings, we created classifiers to predict traveler satisfaction using the best performing rating features. Our results reveal that given our methodology, traveler satisfaction can be predicted with high accuracy. Additionally, we find that training a model on the sentiment of the review text provides a competitive alternative when no five star rating information is available. We believe that our work is of interest for researchers in the area of modeling and predicting user satisfaction based on available review data on the Web.

Paul Seitlinger, Dominik Kowald, Simone Kopeinik et al.

Classic resource recommenders like Collaborative Filtering (CF) treat users as being just another entity, neglecting non-linear user-resource dynamics shaping attention and interpretation. In this paper, we propose a novel hybrid recommendation strategy that refines CF by capturing these dynamics. The evaluation results reveal that our approach substantially improves CF and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant.

Emanuel Lacic, Dominik Kowald, Paul Seitlinger et al.

In this work we present a novel item recommendation approach that aims at improving Collaborative Filtering (CF) in social tagging systems using the information about tags and time. Our algorithm follows a two-step approach, where in the first step a potentially interesting candidate item-set is found using user-based CF and in the second step this candidate item-set is ranked using item-based CF. Within this ranking step we integrate the information of tag usage and time using the Base-Level Learning (BLL) equation coming from human memory theory that is used to determine the reuse-probability of words and tags using a power-law forgetting function. As the results of our extensive evaluation conducted on data-sets gathered from three social tagging systems (BibSonomy, CiteULike and MovieLens) show, the usage of tag-based and time information via the BLL equation also helps to improve the ranking and recommendation process of items and thus, can be used to realize an effective item recommender that outperforms two alternative algorithms which also exploit time and tag-based information.

Emanuel Lacic, Dominik Kowald, Christoph Trattner

In this paper, we present work-in-progress on SocRecM, a novel social recommendation framework for online marketplaces. We demonstrate that SocRecM is not only easy to integrate with existing Web technologies through a RESTful, scalable and easy-to-extend service-based architecture but also reveal the extent to which various social features and recommendation approaches are useful in an online social marketplace environment.

Emanuel Lacic, Dominik Kowald, Lukas Eberhard et al.

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.

Dominik Kowald, Paul Seitlinger, Christoph Trattner et al.

We assume that recommender systems are more successful, when they are based on a thorough understanding of how people process information. In the current paper we test this assumption in the context of social tagging systems. Cognitive research on how people assign tags has shown that they draw on two interconnected levels of knowledge in their memory: on a conceptual level of semantic fields or topics, and on a lexical level that turns patterns on the semantic level into words. Another strand of tagging research reveals a strong impact of time dependent forgetting on users' tag choices, such that recently used tags have a higher probability being reused than "older" tags. In this paper, we align both strands by implementing a computational theory of human memory that integrates the two-level conception and the process of forgetting in form of a tag recommender and test it in three large-scale social tagging datasets (drawn from BibSonomy, CiteULike and Flickr). As expected, our results reveal a selective effect of time: forgetting is much more pronounced on the lexical level of tags. Second, an extensive evaluation based on this observation shows that a tag recommender interconnecting both levels and integrating time dependent forgetting on the lexical level results in high accuracy predictions and outperforms other well-established algorithms, such as Collaborative Filtering, Pairwise Interaction Tensor Factorization, FolkRank and two alternative time dependent approaches. We conclude that tag recommenders can benefit from going beyond the manifest level of word co-occurrences, and from including forgetting processes on the lexical level.

Dominik Kowald, Paul Seitlinger, Christoph Trattner et al.

In this paper, we introduce a tag recommendation algorithm that mimics the way humans draw on items in their long-term memory. This approach uses the frequency and recency of previous tag assignments to estimate the probability of reusing a particular tag. Using three real-world folksonomies gathered from bookmarks in BibSonomy, CiteULike and Flickr, we show how adding a time-dependent component outperforms conventional "most popular tags" approaches and another existing and very effective but less theory-driven, time-dependent recommendation mechanism. By combining our approach with a simple resource-specific frequency analysis, our algorithm outperforms other well-established algorithms, such as FolkRank, Pairwise Interaction Tensor Factorization and Collaborative Filtering. We conclude that our approach provides an accurate and computationally efficient model of a user's temporal tagging behavior. We show how effective principles for information retrieval can be designed and implemented if human memory processes are taken into account.