One particularly promising use case of Large Language Models (LLMs) for recommendation is the automatic generation of Natural Language (NL) user taste profiles from consumption data. These profiles offer interpretable and editable alternatives to opaque collaborative filtering representations, enabling greater transparency and user control. However, it remains unclear whether users consider these profiles to be an accurate representation of their taste, which is crucial for trust and usability. Moreover, because LLMs inherit societal and data-driven biases, profile quality may systematically vary across user and item characteristics. In this paper, we study this issue in the context of music streaming, where personalization is challenged by a large and culturally diverse catalog. We conduct a user study in which participants rate NL profiles generated from their own listening histories. We analyze whether identification with the profiles is biased by user attributes (e.g., mainstreamness, taste diversity) and item features (e.g., genre, country of origin). We also compare these patterns to those observed when using the profiles in a downstream recommendation task. Our findings highlight both the potential and limitations of scrutable, LLM-based profiling in personalized systems.

On music streaming services, listening sessions are often composed of a balance of familiar and new tracks.Recently, sequential recommender systems have adopted cognitive-informed approaches, such as Adaptive Control of Thought-Rational (ACT-R), to successfully improve the prediction of the most relevant tracks for the next user session.However, one limitation of using a model inspired by human memory (or the past), is that it struggles to recommend new tracks that users have not previously listened to.To bridge this gap, here we propose a model that leverages audio information to predict in advance the ACT-R-like activation of new tracks and incorporates them into the recommendation scoring process.We demonstrate the empirical effectiveness of the proposed model using proprietary data, which we publicly release along with the model's source code to foster future research in this field.

Humans have the tendency to discover and explore.This natural tendency is reflected in data from streaming platforms as the amount of previously unknown content accessed by users.Additionally, in domains such as that of music streaming there is evidence that recommending novel content improves users' experience with the platform.Therefore, understanding users' discovery patterns, such as the amount to which and the way users access previously unknown content, is a topic of relevance for both the scientific community and the streaming industry, particularly the music one.Previous works studied how music consumption differs for users of different traits and looked at diversity, novelty, and consistency over time of users' music preferences.However, very little is known about how users discover and explore previously unknown music, and how this behavior differs for users of varying discovery needs.In this paper we bridge this gap by analyzing data from a survey answered by users of the major music streaming platform Deezer in combination with their streaming data.We first address questions regarding whether users who declare a higher interest in unfamiliar music listen to more diverse music, have more stable music preferences over time, and explore more music within a same time window, compared to those who declare a lower interest.We then investigate which type of music tracks users choose to listen to when they explore unfamiliar music, identifying clear patterns of popularity and genre representativeness that vary for users of different discovery needs.Our findings open up possibilities to infer users' interest in unfamiliar music from streaming data as well as possibilities to develop recommender systems that guide users in exploring music in a more natural way .

While the topic of listening context is widely studied in the literature of music recommender systems, the integration of regular user behavior is often omitted. In this paper, we propose PACE (PAttern-based user Consumption Embedding), a framework for building user embeddings that takes advantage of periodic listening behaviors. PACE leverages users’ multichannel time-series consumption patterns to build understandable user vectors. We believe the embeddings learned with PACE unveil much about the repetitive nature of user listening dynamics. By applying this framework on long-term user histories, we evaluate the embeddings through a predictive task of activities performed while listening to music. The validation task’s interest is two-fold, while it shows the relevance of our approach, it also offers an insightful way of understanding users’ musical consumption habits.

Music streaming services often leverage sequential recommender systems to predict the best music to showcase to users based on past sequences of listening sessions. Nonetheless, most sequential recommendation methods ignore or insufficiently account for repetitive behaviors. This is a crucial limitation for music recommendation, as repeatedly listening to the same song over time is a common phenomenon that can even change the way users perceive this song. In this paper, we introduce PISA (Psychology-Informed Session embedding using ACT-R), a session-level sequential recommender system that overcomes this limitation. PISA employs a Transformer architecture learning embedding representations of listening sessions and users using attention mechanisms inspired by Anderson’s ACT-R (Adaptive Control of Thought-Rational), a cognitive architecture modeling human information access and memory dynamics. This approach enables us to capture dynamic and repetitive patterns from user behaviors, allowing us to effectively predict the songs they will listen to in subsequent sessions, whether they are repeated or new ones. We demonstrate the empirical relevance of PISA using both publicly available listening data from Last.fm and proprietary data from Deezer, a global music streaming service, confirming the critical importance of repetition modeling for sequential listening session recommendation. Along with this paper, we publicly release our proprietary dataset to foster future research in this field, as well as the source code of PISA to facilitate its future use.

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.

The traditional recommendation framework seeks to connect user and content, by finding the best match possible based on users past interaction. However, a good content recommendation is not necessarily similar to what the user has chosen in the past. As humans, users naturally evolve, learn, forget, get bored, they change their perspective of the world and in consequence, of the recommendable content. One well known mechanism that affects user interest is the Mere Exposure Effect: when repeatedly exposed to stimuli, users’ interest tends to rise with the initial exposures, reaching a peak, and gradually decreasing thereafter, resulting in an inverted-U shape. Since previous research has shown that the magnitude of the effect depends on a number of interesting factors such as stimulus complexity and familiarity, leveraging this effect is a way to not only improve repeated recommendation but to gain a more in-depth understanding of both users and stimuli. In this work we present (Mere) Exposure2Vec (Ex2Vec) our model that leverages the Mere Exposure Effect in repeat consumption to derive user and item characterization and track user interest evolution. We validate our model through predicting future music consumption based on repetition and discuss its implications for recommendation scenarios where repetition is common.

Transformers emerged as powerful methods for sequential recommendation. However, existing architectures often overlook the complex dependencies between user preferences and the temporal context. In this short paper, we introduce MOJITO, an improved Transformer sequential recommender system that addresses this limitation. MOJITO leverages Gaussian mixtures of attention-based temporal context and item embedding representations for sequential modeling. Such an approach permits to accurately predict which items should be recommended next to users depending on past actions and the temporal context. We demonstrate the relevance of our approach, by empirically outperforming existing Transformers for sequential recommendation on several real-world datasets.

Repetition in music consumption is a common phenomenon. It is notably more frequent when compared to the consumption of other media, such as books and movies. In this paper, we show that one particularly interesting repetitive behavior arises when users are consuming new items. Users’ interest tends to rise with the first repetitions and attains a peak after which interest will decrease with subsequent exposures, resulting in an inverted-U shape. This behavior, which has been extensively studied in psychology, is called the mere exposure effect. In this paper, we show how a number of factors, both content and user-based, well documented in the literature on the mere exposure effect, modulate the magnitude of the effect. Due to the vast availability of data of users discovering new songs everyday in music streaming platforms, this findings enable new ways to characterize both the music, users and their relationships. Ultimately, it opens up the possibility of developing new recommender systems paradigms based on these characterizations.

The search engine of music streaming platforms is a high-control method for navigating the catalog. If one is to study users’ search behavior in this context, one can leverage the vast body of research on general information behavior while challenging previously well validated models with the domain-specific differences. Due to the nature of musical content, users present a series of different needs and behaviors than on traditional web search. For instance, some users employ the search engine as a means to drive their listening session, inputting many queries in close succession not related to the same information goal.

An Unscented Hound for Working Memory (AUHWM) is a new framework for the real-time tracking of human Working Memory (WM) that can be used to adapt computer interfaces to users' available cognitive resources. WM is the part of human cognition responsible for the short term storing and handling of information; it can, in stressful situations, under information overload or when suffering from dementia-like diseases, become severely limited, possibly leading to poor decision making. Our preliminary results suggest that AUHWM can provide a precise and timely assessment of WM capacity, so that the cognitive load a specific task imposes on users can be adapted, e.g., at the User Interface (UI) level. AUHWM is based on a low-level stochastic discrete model of human WM dynamics, implemented as a Gradient-Boosting-derived deterministic algorithm that simulates users' oblivion. AUHWM also performs Unscented Kalman filtering to track users' WM-specific parameters in real time, thus providing a dynamic assessment of their cognitive resources. Our approach has been tested and validated using data collected from Match$ ^2$s, a visual memory game played by 18 users in another study. Going beyond real-time WM tracking, AUHWM is intended to also be used for WM prediction, paving the way to the adaptation of tasks and their UIs in real time as a function of users' cognitive abilities; we detail an example of such an adapted system, and provide experimental evidence this approach could lead to future enhanced WM-adapted UIs.

We introduce MATCHS (Memory Adaptation Through Cognitive Handling Simulation), a new feature for human-computer interaction (HCI) that enables tasks to be more efficiently performed when they heavily depend on a user's working memory (WM) capacity. WM is the part of human cognition responsible for short-term information storage; it is key to the proper completion of one's current task(s). Known to have very limited capacity and a fast decaying time, in particular with age or when Alzheimer-like diseases set in, WM is one of the strongest factors that explain individual differences in cognitive abilities, thus motivating the introduction of WM specific parameters in personalized user interface design. Our MATCHS framework for HCI design builds upon a low level model of the user's WM to predict how much, and for how long, an information can be expected to be stored there. Thus, the task at hand can, accordingly, be dynamically adjusted. We implemented our approach in a new memory game named Match²s, and tested our framework, including with a small set of users. Our results suggest that MATCHS is able to properly assess someone's current WM characteristics and track its evolution as users' motivation or focus evolve over time, providing useful information to adapt simple interaction scenarii such as the one in Match²s. Future work will include more testing and applications, in particular with users for whom such interfaces could be a major asset, i.e., patients suffering from dementia.