Diffusion recommender systems achieve strong recommendation accuracy but often suffer from popularity bias, resulting in unequal item exposure. To address this shortcoming, we introduce A2G-DiffRec, a diffusion recommender that incorporates adaptive autoguidance, where the main model is guided by a less-trained version of itself. Instead of using a fixed guidance weight, A2G-DiffRec learns to adaptively weigh the outputs of the main and weak models during training, supervised by a fairness-aware regularization that promotes balanced exposure across items with different popularity levels. Experimental results on three public datasets show that A2G-DiffRec is effective in enhancing item-side fairness at a marginal cost of accuracy reduction compared to existing guided diffusion recommenders and other non-diffusion baselines.

Music psychology has identified various reasons why people listen to music, based on empirical evidence from interviews and surveys.In this paper, we take a data-driven approach that adopts both pre-trained Sentence Transformers and Cross Encoder, as well as graph-based clustering to first determine music listening intents and then explore user-generated playlists by comparing the title to the listening intents.For this purpose, we first investigated whether 129 established listening functions, previously identified by Schäfer et al. (2013), could be meaningfully clustered into broader listening intents.While Schäfer et al. (2013) introduced three broad dimensions of music listening, this work aimed to identify smaller, context-specific intents to capture more nuanced intents.The resulting clusters were then evaluated through a first survey to select the clusters of the best performing model.In a second survey, music listening intent clusters were explored in more detail to obtain a deeper understanding of their significance for music retrieval and recommendation.Lastly, the playlist selection per intent and characteristics of different listening intents were further explored through a third survey.Given the encouraging results of the evaluation of the computed clusters (92% of clusters judged consistent by participants) and the insight that more than half of the participants search for playlists for a specific intent, we propose a browsing system that categorizes playlists based on their intent and enables users to explore similar playlists.Our approach is further visualized in a dashboard to explore and browse through playlists in intent space.

Calibration is the degree to which a recommender system is able to match the distribution of a certain item attribute among the items consumed by a user with their respective recommendations.Recent work suggests that many recommenders tend to provide miscalibrated recommendations.Furthermore, most approaches aimed at improving calibration adopt the post-processing paradigm, making them computationally costly at the inference time.This work proposes CaliTune, a fine-tuning approach applied to collaborative filtering based recommenders to allow them generate better calibrated recommendations without relying on costly post-processing.We compare CaliTune to an established post-processing approach on two backbone models and datasets from movie and music domains, focusing on popularity calibration.Our results suggest that CaliTune can offer a competitive accuracy-calibration trade-off in several settings, particularly when the backbone model exhibits high miscalibration and accuracy remains important, making it a promising inference-efficient alternative in such cases.

Natural language interfaces offer a compelling approach for music recommendation, enabling users to express complex preferences conversationally. While Large Language Models (LLMs) show promise in this direction, their scalability in recommender systems is limited by high costs and latency. Retrieval-based approaches using smaller language models mitigate these issues but often rely on single-modal item representations, overlook long-term user preferences, and require full model retraining, posing challenges for real-world deployment. In this paper, we present JAM (Just Ask for Music), a lightweight and intuitive framework for natural language music recommendation. JAM models user-query-item interactions as vector translations in a shared latent space, inspired by knowledge graph embedding methods like TransE. To capture the complexity of music and user intent, JAM aggregates multimodal item features via cross-attention and sparse mixture-of-experts. We also introduce JAMSessions, a new dataset of over 100k user-query-item triples with anonymized user/item embeddings, uniquely combining conversational queries and user long-term preferences. Our results show that JAM provides accurate recommendations, produces intuitive representations suitable for practical use cases, and can be easily integrated with existing music recommendation stacks.

Recommender Systems (RS) often rely on representations of users and items in a joint embedding space and on a similarity metric to compute relevance scores.In modern RS, the modules to obtain user and item representations consist of two distinct and separate neural networks (NN).In multimodal representation learning, weight sharing has been proven effective in reducing the distance between multiple modalities of a same item.Inspired by these approaches, we propose a novel RS that leverages weight sharing between the user and item NN modules used to obtain the latent representations in the shared embedding space.The proposed framework consists of a single Collaborative Branch for Recommendation (CoBraR).We evaluate CoBraR by means of quantitative experiments on ecommerce and movie recommendation.Our experiments show that by reducing the number of parameters and improving beyondaccuracy aspects without compromising accuracy, CoBraR has the potential to be applied and extended for real-world scenarios.

Psychological processes play a critical role in shaping users' interactions with information retrieval (IR) and recommender systems (RS). Therefore, understanding human cognition, decision-making, and emotions is vital to enable user-centric retrieval and recommendation systems. Vice versa, understanding whether these aspects are also present in the systems themselves (e.g., in training data, ranking models, or outputs), or even injecting them on purpose, can inform the development of psychology-inspired systems. The purpose of this tutorial is to provide its attendees with an introduction to psychological concepts that are important in the ecosystem of search, retrieval, and recommendation, in particular, cognitive architectures, cognitive effects and biases, as well as personality and affect. Leveraging corresponding models allows its audience to build or refine psychology-informed IR and RS technology. The interdisciplinary tutorial requires intermediate expertise in terms of IR and RS, while we do not assume knowledge in psychology.

This editorial introduces the Special Issue on Trustworthy Recommender Systems , hosted by the ACM Transactions on Recommender Systems in 2024. We provide an overview on the multifaceted aspects of trustworthiness and point to recent regulations that underline the importance of the topic, also beyond technical perspectives. Subsequently, we present the nine articles constituting the special issue: one survey that reviews over 400 papers, categorizing them according to five trustworthiness dimensions, and eight research articles . We categorize and introduce the latter according to the major trustworthiness dimensions they address, specifically into privacy/security , transparency/explainability , and bias/fairness . We provide a summary of their main contributions and end with a brief personal statement about envisioned challenges ahead.

Collaborative filtering-based recommender systems leverage vast amounts of behavioral user data, which poses severe privacy risks. Thus, often random noise is added to the data to ensure Differential Privacy (DP). However, to date, it is not well understood in which ways this impacts personalized recommendations. In this work, we study how DP affects recommendation accuracy and popularity bias when applied to the training data of state-of-the-art recommendation models. Our findings are three-fold: First, we observe that nearly all users’ recommendations change when DP is applied. Second, recommendation accuracy drops substantially while recommended item popularity experiences a sharp increase, suggesting that popularity bias worsens. Finally, we find that DP exacerbates popularity bias more severely for users who prefer unpopular items than for users who prefer popular items.

Many IR systems project harmful societal biases, including gender bias, in their retrieved contents. Uncovering and addressing such biases requires grounded bias measurement principles. However, defining reliable bias metrics for search results is challenging, particularly due to the difficulties in capturing gender-related tendencies in the retrieved documents. In this work, we propose a new framework for search result bias measurement. Within this framework, we first revisit the current metrics for representative search result bias (RepSRB) that are based on the occurrence of gender-specific language in the search results. Addressing their limitations, we additionally propose a metric for comparative search result bias (ComSRB) measurement and integrate it into our framework. ComSRB defines bias as the skew in the set of retrieved documents in response to a non-gendered query toward those for male/female-specific variations of the same query. We evaluate ComSRB against RepSRB on a recent collection of bias-sensitive topics and documents from the MS MARCO collection, using pre-trained bi-encoder and cross-encoder IR models. Our analyses show that, while existing metrics are highly sensitive to the wordings and linguistic formulations, the proposed ComSRB metric mitigates this issue by focusing on the deviations of a retrieval list from its explicitly biased variants, avoiding the need for sub-optimal content analysis processes.

Most recommender systems adopt collaborative filtering (CF) and provide recommendations based on past collective interactions. Therefore, the performance of CF algorithms degrades when few or no interactions are available, a scenario referred to as cold-start. To address this issue, previous work relies on models leveraging both collaborative data and side information on the users or items. Similar to multimodal learning, these models aim at combining collaborative and content representations in a shared embedding space. In this work we propose a novel technique for multimodal recommendation, relying on a multimodal Single-Branch embedding network for Recommendation (SiBraR). Leveraging weight-sharing, SiBraR encodes interaction data as well as multimodal side information using the same single-branch embedding network on different modalities. This makes SiBraR effective in scenarios of missing modality, including cold start. Our extensive experiments on large-scale recommendation datasets from three different recommendation domains (music, movie, and e-commerce) and providing multimodal content information (audio, text, image, labels, and interactions) show that SiBraR significantly outperforms CF as well as state-of-the-art content-based RSs in cold-start scenarios, and is competitive in warm scenarios. We show that SiBraR’s recommendations are accurate in missing modality scenarios, and that the model is able to map different modalities to the same region of the shared embedding space, hence reducing the modality gap.

Recent work suggests that music recommender systems are prone to disproportionally frequent recommendations of music from countries more prominently represented in the training data, notably the US. However, it remains unclear to what extent feedback loops in music recommendation influence the dynamics of such imbalance. In this work, we investigate the dynamics of representation of local (i.e., country-specific) and US-produced music in user profiles and recommendations. To this end, we conduct a feedback loop simulation study using the LFM-2b dataset. The results suggest that most of the investigated recommendation models decrease the proportion of music from local artists in their recommendations. Furthermore, we find that models preserving average proportions of US and local music do not necessarily provide country-calibrated recommendations. We also look into popularity calibration and, surprisingly, find that the most popularity-calibrated model in our study (ItemKNN) provides the least country-calibrated recommendations. In addition, users from less represented countries (e.g., Finland) are, in the long term, most affected by the under-representation of their local music in recommendations.

The Psychology-informed Information Access Systems (PsyIAS) workshop bridges the fields of machine learning and psychology, aiming to connect the research communities of information retrieval, recommender systems, natural language processing, as well as cognitive and behavioral psychology. It serves as a forum for multidisciplinary discussions about the use of psychological constructs, theories, and empirical findings for modeling and predicting user preferences, intents, and behaviors. PsyIAS particularly focuses on research that incorporates such psychology-inspired models into the search, retrieval, and recommendation processes, creates corresponding algorithms and systems, or looks into the role of cognitive processes underlying human information access. More information can be found at https://sites.google.com/view/psyias.

Recommender systems are designed to help us navigate through an abundance of online content. Collaborative filtering (CF) approaches are commonly used to leverage behaviors of others with a similar taste to make predictions for the target user. However, CF is prone to introduce or amplify popularity bias in which popular (often consumed or highly ranked) items are prioritized over less popular items. Many computational metrics of popularity biases — and resulting algorithmic (un)fairness — have been presented. However, it is largely unclear whether these metrics reflect human perception of bias and fairness. We conducted a user study with 170 participants to explore how users perceive recommendation lists created by algorithms with different degrees of popularity bias. Our results show — surprisingly — that popularity biases in recommendation lists are barely observed by users, even when corresponding bias/fairness metrics clearly indicate them.

The provided contents by information retrieval (IR) systems can reflect the existing societal biases and stereotypes. Such biases in retrieval results can lead to further establishing and strengthening stereotypes in society and also in the systems. To facilitate the studies of gender bias in the retrieval results of IR systems, we introduce Gender Representation-Bias for Information Retrieval (Grep-BiasIR), a novel thoroughly-audited dataset consisting of 118 bias-sensitive neutral search queries. The set of queries covers a wide range of gender-related topics, for which a biased representation of genders in the search result can be considered as socially problematic. Each query is accompanied with one relevant and one non-relevant document, where the document is also provided in three variations of female, male, and neutral. The dataset is available at https://github.com/KlaraKrieg/GrepBiasIR.

Music listening sessions often consist of sequences including repeating tracks. Modeling such relistening behavior with models of human memory has been proven effective in predicting the next track of a session. However, these models intrinsically lack the capability of recommending novel tracks that the target user has not listened to in the past. Collaborative filtering strategies, on the contrary, provide novel recommendations by leveraging past collective behaviors but are often limited in their ability to provide explanations. To narrow this gap, we propose four hybrid algorithms that integrate collaborative filtering with the cognitive architecture ACT-R. We compare their performance in terms of accuracy, novelty, diversity, and popularity bias, to baselines of different types, including pure ACT-R, kNN-based, and neural-networks-based approaches. We show that the proposed algorithms are able to achieve the best performances in terms of novelty and diversity, and simultaneously achieve a higher accuracy of recommendation with respect to pure ACT-R models. Furthermore, we illustrate how the proposed models can provide explainable recommendations.

This tutorial provides an interdisciplinary overview about the topics of fairness, non-discrimination, transparency, privacy, and security in the context of recommender systems. These are important dimensions of trustworthy AI systems according to European policies, but also extend to the global debate on regulating AI technology. Since we strongly believe that the aforementioned aspects require more than merely technical considerations, we discuss these topics also from ethical, legal, and regulatory points of views, intertwining different perspectives. The main focus of the tutorial is still on presenting technical solutions that aim at addressing the mentioned topics of trustworthiness. In addition, the tutorial equips the mostly technical audience of RecSys with the necessary understanding of the social and ethical implications of their research and development, and of recent ethical guidelines and regulatory frameworks.

Popularity bias in recommendation lists refers to over-representation of popular content and is a challenge for many recommendation algorithms. Previous research has suggested several offline metrics to quantify popularity bias, which commonly relate the popularity of items in users' recommendation lists to the popularity of items in their interaction history. Discrepancies between these two factors are referred to as popularity miscalibration. While popularity metrics provide a straightforward and well-defined means to measure popularity bias, it is unknown whether they actually reflect users' perception of popularity bias.

We present Travel Bird, a novel personalized destination recommendation and exploration interface which allows its users to find their next tourist destination by describing their specific preferences in a narrative form. Unlike other solutions, Travel Bird is based on TourBERT, a novel NLP model we developed, specifically tailored to the tourism domain. Travel Bird creates a two-dimensional personalized destination exploration space from TourBERT embeddings of social media content and the users' textual description of the experience they are looking for. In this demo, we will showcase several use cases for Travel Bird, which are beneficial for consumers and destination management organizations.

This tutorial aims at providing its audience an interdisciplinary overview about the topics of fairness and non-discrimination, diversity, and transparency as relevant dimensions of trustworthy AI systems, tailored to algorithmic ranking systems such as search engines and recommender systems. We will equip the mostly technical audience of WSDM with the necessary understanding of the social and ethical implications of their research and development on the one hand, and of recent ethical guidelines and regulatory frameworks addressing the aforementioned dimensions on the other hand. While the tutorial foremost takes a European perspective, starting from the concept of trustworthy AI and discussing EU regulation in this area currently in the implementation stages, we also consider related initiatives worldwide. Since ensuring non-discrimination, diversity, and transparency in retrieval and recommendation systems is an endeavor in which academic institutions and companies in different parts of the world should collaborate, this tutorial is relevant for researchers and practitioners interested in the ethical, social, and legal impact of their work. The tutorial, therefore, targets both academic scholars and practitioners around the globe, by reviewing recent research and providing practical examples addressing these particular trustworthiness aspects, and showcasing how new regulations affect the audience's daily work.

User-based KNN recommender systems ( UserKNN ) utilize the rating data of a target user’s k nearest neighbors in the recommendation process. This, however, increases the privacy risk of the neighbors, since the recommendations could expose the neighbors’ rating data to other users or malicious parties. To reduce this risk, existing work applies differential privacy by adding randomness to the neighbors’ ratings, which unfortunately reduces the accuracy of UserKNN . In this work, we introduce ReuseKNN , a novel differentially private KNN-based recommender system. The main idea is to identify small but highly reusable neighborhoods so that (i) only a minimal set of users requires protection with differential privacy and (ii) most users do not need to be protected with differential privacy since they are only rarely exploited as neighbors. In our experiments on five diverse datasets, we make two key observations. Firstly, ReuseKNN requires significantly smaller neighborhoods and, thus, fewer neighbors need to be protected with differential privacy compared with traditional UserKNN . Secondly, despite the small neighborhoods, ReuseKNN outperforms UserKNN and a fully differentially private approach in terms of accuracy. Overall, ReuseKNN leads to significantly less privacy risk for users than in the case of UserKNN .

Personalized recommender systems are essential tools to facilitate human decision making. Many contemporary recommender systems use advanced machine learning techniques to model and predict user preferences from behavioral data. While such systems can provide helpful recommendations, their algorithms’ design does not incorporate the underlying psychological mechanisms that shape user preferences and behavior. In this tutorial, we will guide the attendees through the state-of-the-art in psychology-informed recommender systems, i.e., recommender systems that consider extrinsic and intrinsic human factors. We show how such systems can improve the recommendation process in a user-centric fashion.

We present the LFM-2b dataset containing the listening records of over 120,000 users of the music platform Last.fm. These users provide a total of more than two billion individual listening events that span a time range of over 15 years, from February 2005 until March 2020. These listening events refer to a total of 50 million distinct tracks of 5 million distinct artists. Beside the common metadata (i. e., artist and track name), LFM-2b contains additional information both regarding the users and items. This includes the demographic information of users, namely country, gender, and age, and the fine-grained genre and style of items together with the vector embeddings of their lyrics.

When we appreciate a piece of music, it is most naturally because of its content, including rhythmic, tonal, and timbral elements as well as its lyrics and semantics. This suggests that the human affinity for music is inherently content-driven. This kind of information is, however, still frequently neglected by mainstream recommendation models based on collaborative filtering that rely solely on user-item interactions to recommend items to users. A major reason for this neglect is the lack of standardized datasets that provide both collaborative and content information. The work at hand addresses this shortcoming by introducing Music4All-Onion, a large-scale, multi-modal music dataset. The dataset expands the Music4All dataset by including 26 additional audio, video, and metadata characteristics for 109,269 music pieces. In addition, it provides a set of 252,984,396 listening records of 119,140 users, extracted from the online music platform Last.fm, which allows leveraging user-item interactions as well. We organize distinct item content features in an onion model according to their semantics, and perform a comprehensive examination of the impact of different layers of this model (e.g., audio features, user-generated content, and derivative content) on content-driven music recommendation, demonstrating how various content features influence accuracy, novelty, and fairness of music recommendation systems. In summary, with Music4All-Onion, we seek to bridge the gap between collaborative filtering music recommender systems and content-centric music recommendation requirements.

We introduce Emotion-aware Music Tower Blocks (EmoMTB), an audiovisual interface to explore large music collections. It creates a musical landscape, by adopting the metaphor of a city, where similar songs are grouped into the same building and nearby buildings form neighborhoods of particular genres. In order to personalize the user experience, an underlying classifier monitors textual user-generated content, by predicting their emotional state and adapting the audiovisual elements of the interface accordingly. EmoMTB enables users to explore different musical styles either within their comfort zone or outside of it. Besides, tailoring the results of the recommender engine to match the affective state of the user, EmoMTB offers a unique way to discover and enjoy music. EmoMTB supports exploring a collection of circa half a million streamed songs using a regular smartphone as a control interface to navigate in the landscape.

Recommender systems are essential tools to support human decision-making in online information spaces. Many state-of-the-art recommender systems adopt advanced machine learning techniques to model and predict user preferences from behavioral data. While such systems can provide useful and effective recommendations, their algorithmic design commonly neglects underlying psychological mechanisms that shape user preferences and behavior. In this tutorial, we offer a comprehensive review of the state of the art and progress in psychology-informed recommender systems, i.e., recommender systems that incorporate human cognitive processes, personality, and affective cues into recommendation models, along with definitions, strengths and weaknesses. We show how such systems can improve the recommendation process in a user-centric fashion. With this tutorial, we aim to stimulate more ideas and discussion with the audience on core issues of this topic such as the identification of suitable psychological models, availability of datasets, or the suitability of existing performance metrics to evaluate the efficacy of psychology-informed recommender systems. Besides, we present takeaways to recommender systems practitioners how to build psychology-informed recommender systems. Previous versions of this tutorial were presented, among others, at The ACM Web Conference 2022 and the ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR) 2022.

Recent studies show the benefits of reformulating common machine learning models through the concept of prototypes – representatives of the underlying data, used to calculate the prediction score as a linear combination of similarities of a data point to prototypes. Such prototype-based formulation of a model, in addition to preserving (sometimes enhancing) the performance, enables explainability of the model’s decisions, as the prediction can be linearly broken down into the contributions of distinct definable prototypes. Following this direction, we extend the idea of prototypes to the recommender system domain by introducing ProtoMF, a novel collaborative filtering algorithm. ProtoMF learns sets of user/item prototypes that represent the general consumption characteristics of users/items in the underlying dataset. Using these prototypes, ProtoMF then represents users and items as vectors of similarities to the corresponding prototypes. These user/item representations are ultimately leveraged to make recommendations that are both effective in terms of accuracy metrics, and explainable through the interpretation of prototypes’ contributions to the affinity scores. We conduct experiments on three datasets to assess both the effectiveness and the explainability of ProtoMF. Addressing the former, we show that ProtoMF exhibits higher Hit Ratio and NDCG compared to other relevant collaborative filtering approaches. As for the latter, we qualitatively show how ProtoMF can provide explainable recommendations and how its explanation capabilities can expose the existence of statistical biases in the learned representations, which we exemplify for the case of gender bias.

Collaborative filtering algorithms capture underlying consumption patterns, including the ones specific to particular demographics or protected information of users, e.g., gender, race, and location. These encoded biases can influence the decision of a recommendation system (RS) towards further separation of the contents provided to various demographic subgroups, and raise privacy concerns regarding the disclosure of users' protected attributes. In this work, we investigate the possibility and challenges of removing specific protected information of users from the learned interaction representations of a RS algorithm, while maintaining its effectiveness. Specifically, we incorporate adversarial training into the state-of-the-art MultVAE architecture, resulting in a novel model, Adversarial Variational Auto-Encoder with Multinomial Likelihood (Adv-MultVAE), which aims at removing the implicit information of protected attributes while preserving recommendation performance. We conduct experiments on the MovieLens-1M and LFM-2b-DemoBias datasets, and evaluate the effectiveness of the bias mitigation method based on the inability of external attackers in revealing the users' gender information from the model. Comparing with baseline MultVAE, the results show that Adv-MultVAE, with marginal deterioration in performance (w.r.t. NDCG and recall), largely mitigates inherent biases in the model on both datasets.

This tutorial aims at providing its audience an interdisciplinary overview about the topics of fairness and non-discrimination, diversity, and transparency of AI systems, tailored to the research fields of information retrieval and recommender systems. By means of this tutorial, we would like to equip the mostly technical audience of SIGIR with the necessary understanding of the ethical implications of their research and development on the one hand, and of recent political and legal regulations that address the aforementioned challenges on the other hand.

Homophily describes the phenomenon that similarity breeds connection, i.e., individuals tend to form ties with other people who are similar to themselves in some aspect(s). The similarity in music taste can undoubtedly influence who we make friends with and shape our social circles. In this paper, we study homophily in an online music platform Last.fm regarding user preferences towards listening to mainstream (M), novel (N), or diverse (D) content. Furthermore, we draw comparisons with homophily based on listening profiles derived from artists users have listened to in the past, i.e., artist profiles. Finally, we explore the utility of users' artist profiles as well as features describing M, N, and D for the task of link prediction. Our study reveals that: (i) users with a friendship connection share similar music taste based on their artist profiles; (ii) on average, a measure of how diverse is the music two users listen to is a stronger predictor of friendship than measures of their preferences towards mainstream or novel content, i.e., homophily is stronger for D than for M and N; (iii) some user groups such as high-novelty-seekers (explorers) exhibit strong homophily, but lower than average artist profile similarity; (iv) using M, N and D achieves comparable results on link prediction accuracy compared with using artist profiles, but the combination of features yields the best accuracy results, and (v) using combined features does not add value if graph-based features such as common neighbors are available, making M, N, and D features primarily useful in a cold-start user recommendation setting for users with few friendship connections. The insights from this study will inform future work on social context-aware music recommendation, user modeling, and link prediction.

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 τ 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.

Providing suitable recommendations is of vital importance to improve the user satisfaction of music recommender systems. Here, users often listen to the same track repeatedly and appreciate recommendations of the same song multiple times. Thus, accounting for users’ relistening behavior is critical for music recommender systems. In this paper, we describe a psychology-informed approach to model and predict music relistening behavior that is inspired by studies in music psychology, which relate music preferences to human memory. We adopt a well-established psychological theory of human cognition that models the operations of human memory, i.e., Adaptive Control of Thought—Rational (ACT-R). In contrast to prior work, which uses only the base-level component of ACT-R, we utilize five components of ACT-R, i.e., base-level, spreading, partial matching, valuation, and noise, to investigate the effect of five factors on music relistening behavior: (i) recency and frequency of prior exposure to tracks, (ii) co-occurrence of tracks, (iii) the similarity between tracks, (iv) familiarity with tracks, and (v) randomness in behavior. On a dataset of 1.7 million listening events from Last.fm, we evaluate the performance of our approach by sequentially predicting the next track(s) in user sessions. We find that recency and frequency of prior exposure to tracks is an effective predictor of relistening behavior. Besides, considering the co-occurrence of tracks and familiarity with tracks further improves performance in terms of R-precision. We hope that our work inspires future research on the merits of considering cognitive aspects of memory retrieval to model and predict complex user behavior.

Podcasts are spoken documents across a wide-range of genres and styles, with growing listenership across the world, and a rapidly lowering barrier to entry for both listeners and creators. The great strides in search and recommendation in research and industry have yet to see impact in the podcast space, where recommendations are still largely driven by word of mouth. In this perspective paper, we highlight the many differences between podcasts and other media, and discuss our perspective on challenges and future research directions in the domain of podcast information access.

Societal biases resonate in the retrieved contents of information retrieval (IR) systems, resulting in reinforcing existing stereotypes. Approaching this issue requires established measures of fairness in respect to the representation of various social groups in retrieval results, as well as methods to mitigate such biases, particularly in the light of the advances in deep ranking models. In this work, we first provide a novel framework to measure the fairness in the retrieved text contents of ranking models. Introducing a ranker-agnostic measurement, the framework also enables the disentanglement of the effect on fairness of collection from that of rankers. To mitigate these biases, we propose AdvBert, a ranking model achieved by adapting adversarial bias mitigation for IR, which jointly learns to predict relevance and remove protected attributes. We conduct experiments on two passage retrieval collections (MSMARCO Passage Re-ranking and TREC Deep Learning 2019 Passage Re-ranking), which we extend by fairness annotations of a selected subset of queries regarding gender attributes. Our results on the MSMARCO benchmark show that, (1) all ranking models are less fair in comparison with ranker-agnostic baselines, and (2) the fairness of Bert rankers significantly improves when using the proposed AdvBert models. Lastly, we investigate the trade-off between fairness and utility, showing that we can maintain the significant improvements in fairness without any significant loss in utility.

Click logs are valuable resources for a variety of information retrieval (IR) tasks. This includes query understanding/analysis, as well as learning effective IR models particularly when the models require large amounts of training data. We release a large-scale domain-specific dataset of click logs, obtained from user interactions of the Trip Database health web search engine. Our click log dataset comprises approximately 5.2 million user interactions collected between 2013 and 2020. We use this dataset to create a standard IR evaluation benchmark - TripClick - with around 700,000 unique free-text queries and 1.3 million pairs of query-document relevance signals, whose relevance is estimated by two click-through models. As such, the collection is one of the few datasets offering the necessary data richness and scale to train neural IR models with a large amount of parameters, and notably the first in the health domain. Using TripClick, we conduct experiments to evaluate a variety of IR models, showing the benefits of exploiting this data to train neural architectures. In particular, the evaluation results show that the best performing neural IR model significantly improves the performance by a large margin relative to classical IR models, especially for more frequent queries.

Although recommender systems (RSs) play a crucial role in our society, previous studies have revealed that the performance of RSs may considerably differ between groups of individuals with different characteristics or from different demographics. In this case, a RS is considered to be unfair when it does not perform equally well for different groups of users. Considering the importance of RSs in the distribution and consumption of musical content worldwide, a careful evaluation of fairness in the context of music RSs is crucial. To this end, we first introduce LFM-2b, a novel large-scale real-world dataset of music listening records, comprising a subset to investigate bias of RSs regarding users’ demographics. We then define a notion of fairness based on the performance gap of a RS between the users with different demographics, and evaluate a variety of collaborative filtering algorithms in terms of accuracy and beyond-accuracy metrics to explore the fairness in the RS results toward a specific gender group. We observe the existence of significant discrepancies (unfairness) between the performance of algorithms across male and female user groups. Based on these discrepancies, we explore to what extent recommender algorithms lead to intensifying the underlying population bias in the final results. We also study the effect of a resampling strategy, commonly used as debiasing method , which yields slight improvements in the fairness measures of various algorithms while maintaining their accuracy and beyond-accuracy performance.

We present Music Tower Blocks, a novel browsing interface for interactive music visualization, capable of dealing with web-scale music collections nowadays offered by major music streaming services. Based on a clustering created from fused metadata and acoustic features, a block-based skyline landscape is constructed. It can be navigated by the user in several ways (zooming, panning, changing angle of slope). User-adjustable color coding is used for highlighting various facets, e.g., visualizing the distributions of genres and acoustic features. Furthermore, several search and filtering capabilities are provided (e.g., search for artists and tracks; filtering with respect to track popularity to focus on top hits or discovering unknown gems). In addition, Music Tower Blocks offers the user to connect to their personal music streaming profiles and highlight on the landscape their favorite or recently-listened-to music, to support exploring parts of the landscape near to (or far-away from) their own taste.

Recommender systems, like other tools that make use of machine learning, are known to create or increase certain biases. Earlier work has already unveiled different performance of recommender systems for different user groups, depending on gender, age, country, and consumption behavior. In this work, we study user bias in terms of another aspect, i.e., users’ personality. We investigate to which extent state-of-the-art recommendation algorithms yield different accuracy scores depending on the users’ personality traits. We focus on the music domain and create a dataset of Twitter users’ music consumption behavior and personality traits, measuring the latter in terms of the OCEAN model. Investigating [email protected] and [email protected] of the recommendation algorithms SLIM, embarrassingly shallow autoencoders for sparse data (EASE), and variational autoencoders for collaborative filtering (Mult-VAE) on this dataset, we find several significant differences in performance between user groups scoring high vs. groups scoring low on several personality traits.

Concerns regarding the footprint of societal biases in information retrieval (IR) systems have been raised in several previous studies. In this work, we examine various recent IR models from the perspective of the degree of gender bias in their retrieval results. To this end, we first provide a bias measurement framework which includes two metrics to quantify the degree of the unbalanced presence of gender-related concepts in a given IR model's ranking list. To examine IR models by means of the framework, we create a dataset of non-gendered queries, selected by human annotators. Applying these queries to the MS MARCO Passage retrieval collection, we then measure the gender bias of a BM25 model and several recent neural ranking models. The results show that while all models are strongly biased toward male, the neural models, and in particular the ones based on contextualized embedding models, significantly intensify gender bias. Our experiments also show an overall increase in the gender bias of neural models when they exploit transfer learning, namely when they use (already biased) pre-trained embeddings.

Music is known to exhibit different characteristics, depending on genre and style. While most research that studies such differences takes a musicological perspective and analyzes acoustic properties of individual pieces or artists, we conduct a large-scale analysis using various web resources. Exploiting content information from song lyrics, contextual information reflected in music artists' Wikipedia articles, and listening information, we particularly study the aspects of popularity, length, repetitiveness, and readability of lyrics and Wikipedia articles. We measure popularity in terms of song play count (PC) and listener count (LC), length in terms of character and word count, repetitiveness in terms of text compression ratio, and readability in terms of the Simple Measure of Gobbledygook (SMOG). Extending datasets of music listening histories and genre annotations from Last.fm, we extract and analyze 424,476 song lyrics by 18,724 artists from LyricWiki.

The ACM Recommender Systems Challenge 2018 focused on the task of automatic music playlist continuation, which is a form of the more general task of sequential recommendation. Given a playlist of arbitrary length with some additional meta-data, the task was to recommend up to 500 tracks that fit the target characteristics of the original playlist. For the RecSys Challenge, Spotify released a dataset of one million user-generated playlists. Participants could compete in two tracks, i.e., main and creative tracks. Participants in the main track were only allowed to use the provided training set, however, in the creative track, the use of external public sources was permitted. In total, 113 teams submitted 1,228 runs to the main track; 33 teams submitted 239 runs to the creative track. The highest performing team in the main track achieved an R-precision of 0.2241, an NDCG of 0.3946, and an average number of recommended songs clicks of 1.784. In the creative track, an R-precision of 0.2233, an NDCG of 0.3939, and a click rate of 1.785 was obtained by the best team. This article provides an overview of the challenge, including motivation, task definition, dataset description, and evaluation. We further report and analyze the results obtained by the top-performing teams in each track and explore the approaches taken by the winners. We finally summarize our key findings, discuss generalizability of approaches and results to domains other than music, and list the open avenues and possible future directions in the area of automatic playlist continuation.

The ACM Recommender Systems Challenge 2018 focused on automatic music playlist continuation, which is a form of the more general task of sequential recommendation. Given a playlist of arbitrary length, the challenge was to recommend up to 500 tracks that fit the target characteristics of the original playlist. For the Challenge, Spotify released a dataset of one million user-created playlists, along with associated metadata. Participants could submit their approaches in two tracks, i.e., main and creative tracks, where the former allowed teams to use solely the provided dataset and the latter allowed them to exploit publicly available external data too. In total, 113 teams submitted 1,228 runs in the main track; 33 teams submitted 239 runs in the creative track. The highest performing team in the main track achieved an R-precision of 0.2241, an NDCG of 0.3946, and an average number of recommended songs clicks of 1.784. In the creative track, an R-precision of 0.2233, an NDCG of 0.3939, and a click rate of 1.785 was realized by the best team.

We propose a multi-modal content-based movie recommender system that replaces human-generated metadata with content descriptions automatically extracted from the visual and audio channels of a video. Content descriptors improve over traditional metadata in terms of both richness (it is possible to extract hundreds of meaningful features covering various modalities) and quality (content features are consistent across different systems and immune to human errors). Our recommender system integrates state-of-the-art aesthetic and deep visual features as well as block-level and i-vector audio features. For fusing the different modalities, we propose a rank aggregation strategy extending the Borda count approach.

This tutorial introduces multimedia recommender systems (MMRS), in particular, recommender systems that leverage multimedia content to recommend different media types. In contrast to the still most frequently adopted collaborative filtering approaches, we focus on content-based MMRS and on hybrids of collaborative filtering and content-based filtering. The target recommendation domains of the tutorial are movies, music and images. We present state-of-the-art approaches for multimedia feature extraction (text, audio, visual), including deep learning methods, and recommendation approaches tailored to the multimedia domain. Furthermore, by introducing common evaluation techniques, pointing to publicly available datasets specific to the multimedia domain, and discussing the grand challenges in MMRS research, this tutorial provides the audience with a profound introduction to MMRS and an inspiration to conduct further research.

The particularities of musical data and its multiple modalities make original contributions possible in many core RecSys topics such as content-based and hybrid recommendation, user modeling, interfaces, and context-aware and mobile recommendations. But more urgently, the current revolution in the music industry represents major opportunities and challenges for recommendation systems in general. Recommendation systems are now central to music streaming platforms, which are rapidly increasing in listenership and becoming the top source of revenue for the music industry. It is increasingly more common for a music listener to simply access music than to purchase and own it in a personal collection. In this scenario, recommendation calls no longer for a one-shot recommendation for the purpose of a track or album purchase, but for a recommendation of a listening experience, comprising a very wide range of challenges, such as sequential recommendation, or conversational and contextual recommendations. Recommendation technologies now impact all actors in the rich and complex music industry ecosystem (listeners, labels, music makers and producers, concert halls, advertisers, etc.). To highlight these developments, we focus on three use cases: automatic playlist generation, context-aware music recommendation, and recommendation in the creative process of music making.

Intelligent technologies have become an essential part of music systems and applications. This is evidenced by today's omnipresence of digital online music stores and streaming services, which rely on music recommenders, automatic playlist generators, and music browsing interfaces. A large amount of research leading to intelligent music applications deals with the extraction of musical and acoustic information directly from the audio signal using signal processing techniques. Other strategies exploit contextual aspects of music, not present in the signal, for example, community meta-data and trails of user interaction, as found, for instance, on social media platforms. In this editorial, we discuss the notion of “intelligent music system” and give an overview of the papers selected to this special issue.

We present the LFM-1b dataset of more than one billion music listening events created by more than 120,000 users of Last.fm. Each listening event is characterized by artist, album, and track name, and further includes a timestamp. On the (anonymous) user level, basic demographics and a selection of more elaborate user descriptors are included.

This paper reports on three demonstrators developed to provide personalized, enhanced experiences of classical music, within the EU FP7 project "Performances as Highly Enriched aNd Interactive Concert eXperiences" (PHENICX): (i) an interface for accessing supplemental multimodal material about music items, (ii) a recommender system for visualizations of classical music, and (iii) a recommender system for tagging. The personalization in all three demos is achieved through modeling users' personality and musical sophistication. The links to the web interfaces are provided as well as the outcomes of quantitative and qualitative evaluations.

In this tutorial, we give an introduction to the field of and state of the art in music information retrieval (MIR). The tutorial particularly spotlights the question of music similarity, which is an essential aspect in music retrieval and recommendation. Three factors play a central role in MIR research: (1) the music content, i.e., the audio signal itself, (2) the music context, i.e., metadata in the widest sense, and (3) the listeners and their contexts, manifested in user-music interaction traces. We review approaches that extract features from all three data sources and combinations thereof and show how these features can be used for (large-scale) music indexing, music description, music similarity measurement, and recommendation. These methods are further showcased in a number of popular music applications, such as automatic playlist generation and personalized radio stationing, location-aware music recommendation, music search engines, and intelligent browsing interfaces. Additionally, related topics such as music identification, automatic music accompaniment and score following, and search and retrieval in the music production domain are discussed.

A shortcoming of current approaches for music recommendation is that they consider user-specific characteristics only on a very simple level, typically as some kind of interaction between users and items when employing collaborative filtering. To alleviate this issue, we propose several user features that model aspects of the user's music listening behavior: diversity, mainstreaminess, and novelty of the user's music taste. To validate the proposed features, we conduct a comprehensive evaluation of a variety of music recommendation approaches (stand-alone and hybrids) on a collection of almost 200 million listening events gathered from \propername{Last.fm}. We report first results and highlight cases where our diversity, mainstreaminess, and novelty features can be beneficially integrated into music recommender systems.

The amount of music consumed while on the move has been spiraling during the past couple of years, which requests for intelligent music recommendation techniques. In this demo paper, we introduce a context-aware mobile music player named "Mobile Music Genius" (MMG), which seamlessly adapts the music playlist on the fly, according to the user context. It makes use of a comprehensive set of features derived from sensor data, spatiotemporal information, and user interaction to learn which kind of music a listeners prefers in which context. We describe the automatic creation and adaptation of playlists and present results of a study that investigates the capabilities of the gathered user context features to predict the listener's music preference.

The SoMeRA workshop targets cutting edge research from all fields of retrieval, recommendation, and browsing in social media, as well as the analysis of user's multifaceted traces therein. Submissions to the workshop cover a broad range of topics including multimedia retrieval and exploration, user-aware recommender systems, network analysis, event detection, and computational linguistics.

Music information retrieval and music recommendation are seeing a paradigm shift towards methods that incorporate user context aspects. However, structured experiments on a standardized music dataset to investigate the effects of doing so are scarce. In this paper, we compare performance of various combinations of collaborative filtering and geospatial as well as cultural user models for the task of music recommendation. To this end, we propose a geospatial model that uses GPS coordinates and a cultural model that uses semantic locations (continent, country, and state of the user). We conduct experiments on a novel standardized music collection, the ``Million Musical Tweets Dataset'' of listening events extracted from microblogs. Overall, we find that modeling listeners' location via Gaussian mixture models and computing similarities from these outperforms both cultural user models and collaborative filtering.

In this paper we approach the issue of violence detection in typical Hollywood productions. Given the high variability in appearance of violent scenes in movies, training a classifier to predict violent frames directly from visual or/and auditory features seems rather difficult. Instead, we propose a different perspective that relies on fusing mid-level concept predictions that are inferred from low-level features. This is achieved by employing a bank of multi-layer perceptron classifiers featuring a dropout training scheme. Experimental validation conducted in the context of the Violent Scenes Detection task of the MediaEval 2012 Multimedia Benchmark Evaluation show the potential of this approach that ranked first among 34 other submissions in terms of precision and F1-score.

We propose a novel approach to context-aware music recommendation - recommending music suited for places of interest (POIs). The suggested hybrid approach combines two techniques -- one based on representing both POIs and music with tags, and the other based on the knowledge of the semantic relations between the two types of items. We show that our approach can be scaled up using a novel music auto-tagging technique and we compare it in a live user study to: two non-hybrid solutions, either based on tags or on semantic relations; and to a context-free but personalized recommendation approach. In the considered scenario, i.e., a situation defined by a context (the POI), we show that personalization (via music preference) is not sufficient and it is important to implement effective adaptation techniques to the user's context. In fact, we show that the users are more satisfied with the recommendations generated by combining the tag-based and knowledge-based context adaptation techniques, which exploit orthogonal types of relations between places and music tracks.

This tutorial serves as an introductory course to the field of and state-of-the-art in music information retrieval (MIR) and in particular to music similarity estimation which is an essential component of music retrieval. Apart from explaining approaches that estimate similarity based on acoustic properties of an audio signal, we review methods that exploit (mostly textual) meta-data from the Web to build representations of music then used for similarity calculation. Additionally, topics such as (large-scale) music indexing, information extraction for music, personalization in music retrieval, and evaluation of MIR systems are addressed.

Recent advances in music retrieval and recommendation algorithms highlight the necessity to follow multimodal approaches in order to transcend limits imposed by methods that solely use audio, web, or collaborative filtering data. In this paper, we propose hybrid music recommendation algorithms that combine information on the music content, the music context, and the user context, in particular, integrating location-aware weighting of similarities. Using state-of-the-art techniques to extract audio features and contextual web features, and a novel standardized data set of music listening activities inferred from microblogs (MusicMicro), we propose several multimodal retrieval functions.

Personalization and context-awareness are highly important topics in research on Intelligent Information Systems. In the fields of Music Information Retrieval (MIR) and Music Recommendation in particular, user-centric algorithms should ideally provide music that perfectly fits each individual listener in each imaginable situation and for each of her information or entertainment needs. Even though preliminary steps towards such systems have recently been presented at the “International Society for Music Information Retrieval Conference” (ISMIR) and at similar venues, this vision is still far away from becoming a reality. In this article, we investigate and discuss literature on the topic of user-centric music retrieval and reflect on why the breakthrough in this field has not been achieved yet. Given the different expertises of the authors, we shed light on why this topic is a particularly challenging one, taking computer science and psychology points of view. Whereas the computer science aspect centers on the problems of user modeling, machine learning, and evaluation, the psychological discussion is mainly concerned with proper experimental design and interpretation of the results of an experiment. We further present our ideas on aspects crucial to consider when elaborating user-aware music retrieval systems.

Mobile music consumption has been spiraling during the past couple of years. The interaction techniques provided to sift through the ever increasing amounts of music available on smart devices unfortunately have not. In this paper, we address this issue and present an intelligent mobile user interface that enables the user to browse her mobile music collection in a joyful and informed way.

Different term weighting techniques such as $$TF\cdot IDF$$ or BM25 have been used intensely for manifold text-based information retrieval tasks. Their use for modeling term profiles for named entities and subsequent calculation of similarities between these named entities have been studied to a much smaller extent. The recent trend of microblogging made available massive amounts of information about almost every topic around the world. Therefore, microblogs represent a valuable source for text-based named entity modeling. In this paper, we present a systematic and comprehensive evaluation of different term weighting measures, normalization techniques, query schemes, index term sets, and similarity functions for the task of inferring similarities between named entities, based on data extracted from microblog posts. We analyze several thousand combinations of choices for the above mentioned dimensions, which influence the similarity calculation process, and we investigate in which way they impact the quality of the similarity estimates. Evaluation is performed using three real-world data sets: two collections of microblogs related to music artists and one related to movies. For the music collections, we present results of genre classification experiments using as benchmark genre information from allmusic.com . For the movie collection, we present results of multi-class classification experiments using as benchmark categories from IMDb . We show that microblogs can indeed be exploited to model named entity similarity with remarkable accuracy, provided the correct settings for the analyzed aspects are used. We further compare the results to those obtained when using Web pages as data source.

In this paper, we provide an overview of the 3rd International Workshop on Search and Mining User-generated Contents, held in conjunction with the 20th ACM International Conference on Information and Knowledge Management. We present the motivation and goals of the workshop, and some statistics and details about accepted papers and keynotes.

We present a novel user interface that offers a fun way to explore music collections in virtual landscapes in a game-like manner. Extending previous work, special attention is paid to scalability and user interaction. In this vein, the ever growing size of today's music collections is addressed in two ways that allow for visualizing and browsing nearly arbitrarily sized music repositories. First, the proposed user interface deepTune employs a hierarchical version of the Self-Organizing Map (SOM) to cluster similar pieces of music using multiple, hierarchically aligned layers. Second, to facilitate orientation in the landscape by presenting well-known anchor points to the user, a combination of Web-based and audio signal-based information extraction techniques to determine cluster prototypes (songs) is proposed. Selecting representative and well-known prototypes -- the former is ensured by using signal-based features, the latter by using Web-based data -- is crucial for browsing large music collections. We further report on results of an evaluation carried out to assess the quality of the proposed cluster prototype ranking.

This article comprehensively addresses the problem of similarity measurement between music artists via text-based features extracted from Web pages. To this end, we present a thorough evaluation of different term-weighting strategies, normalization methods, aggregation functions, and similarity measurement techniques. In large-scale genre classification experiments carried out on real-world artist collections, we analyze several thousand combinations of settings/parameters that influence the similarity calculation process, and investigate in which way they impact the quality of the similarity estimates. Accurate similarity measures for music are vital for many applications, such as automated playlist generation, music recommender systems, music information systems, or intelligent user interfaces to access music collections by means beyond text-based browsing. Therefore, by exhaustively analyzing the potential of text-based features derived from artist-related Web pages, this article constitutes an important contribution to context-based music information research.

We propose three heuristics to determine the country of origin of a person or institution via text-based IE from the Web. We evaluate all methods on a collection of music artists and bands, and show that some heuristics outperform earlier work on the topic by terms of coverage, while retaining similar precision levels. We further investigate an extension using country-specific synonym lists.

An approach is presented to automatically build a search engine for large-scale music collections that can be queried through natural language. While existing approaches depend on explicit manual annotations and meta-data assigned to the individual audio pieces, we automatically derive descriptions by making use of methods from Web Retrieval and Music Information Retrieval. Based on the ID3 tags of a collection of mp3 files, we retrieve relevant Web pages via Google queries and use the contents of these pages to characterize the music pieces and represent them by term vectors. By incorporating complementary information about acous tic similarity we are able to both reduce the dimensionality of the vector space and improve the performance of retrieval, i.e. the quality of the results. Furthermore, the usage of audio similarity allows us to also characterize audio pieces when there is no associated information found on the Web.