1. Introduction & Related Work
There has been an increased interest in understanding online behaviors with psychological models and incorporating them to personalize systems (e.g., (Ferwerda and Schedl, 2016)). Using psychological models to infer user characteristics from behavior has the advantage that personalization can be done without the need of additional, explicit data collection. Hence, it can be used to mitigate problems where data is scarce (e.g., the cold-start problem).
Most of the research on using psychological models in technological contexts rely on personality traits of users. Personality is a general model to categorize users and can even be used across domains (Fernández-Tobías and Cantador, 2015). However, using more domain dependent psychological models allows for more fine-grained identification of behaviors. Recent research are tapping into these domain dependent psychological models to improve personalizations. For example, Graus et al. (2018) showed that personalization based on parenting styles improved the overall user experience of an online parenting library. Hauser et al. (2009) exploited the cognitive styles of website users to provide a personalized experience. Germanakos et al. (2016) looked at learning styles to adapt the learning environment of students.
In this preliminary work we look at the music domain and explore the influence of musical sophistication and the possibilities to infer musical sophistication of users from their music listening behavior. Müllensiefen et al. (2014) created a survey that measures musical sophistication which they define as ”a psychometric construct that can refer to musical skills, expertise, achievements, and related behaviors across a range of facets that are measured on different subscales.” This translates to that people with a higher degree of music sophistication in general engage more frequently in musical skills and behaviors, and have a greater and more varied repertoire of music behavior patterns. Hence, people’s musical sophistication may well be reflected in their music listening patterns. In addition, musical sophistication has been suggested to be related to peoples’ needs with regards to music systems (Celma, 2010). The rise of online music services allows for tracking and analyzing music listening behavior on a larger scale. It provides opportunities to gain deeper insights on the relationships between music sophistication and listening behavior, as well as inferring musical sophistication from listening behaviors.
The data for this study was collected as part of a larger study that investigated how the order of individual songs affects playlist experience. To study the relationship between musical sophistication and music listening behavior, participants’ logged into our app through the Spotify API, which allowed us to retrieve their music listening behavior. In addition, participants completed a survey with items from the Goldmiths Musical Sophistication Index (Gold-MSI; (Müllensiefen et al., 2014)). The Gold-MSI measures musical sophistication on five subscales: active engagement, emotions, singing abilities, perceptual abilities, and musical training. However, in this preliminary work, we only asked participants to respond on two of these subscales as we believe that they are the most prominent ones reflected in online music listening behaviors:
Active engagement (e.g., how much time and money one spends on music; measured by 9-items).
Emotions (e.g., active behaviors related to emotional responses to music; measured by 6-items).
A total of 61 participants were recruited in December 2017 through a participant pool managed by the Human-Technology Interaction group at Eindhoven University of Technology: 28 male, 33 female (mean age: 23.92 years, SD: 4.57 years). Using Spotify’s API we retrieved the participants’ top tracks, which resulted in a dataset of 21,080 tracks. For each track we retrieved the audio features through Spotify’s API: valence (0-1: negative-positive emotions), liveness, instrumentalness, energy (0-1: calm-energetic), danceability, tempo (BPM), time signature, loudness (dB), track popularity and artist popularity. 111Popularity measures are not explained in detail by Spotify, but range from 0 to 100.
For each feature we calculated the standard deviation, mean, median, min and max values.
We used a learner-based feature selection to select the best features (track properties) to create a model to predict participants’ emotions and active engagement scores(Müllensiefen et al., 2014)
from their music listening behaviors. A ZeroR classifier was used to create a baseline predictive model. Two different classifiers were used and compared against the baseline model: random forest and radial basis function network (RBF network). Each classifier was applied to the selected features (see Table1).
Our predictive models were trained with the aforementioned classifiers in Weka (Hall et al., 2009) with a 10-fold cross-validation with 10 iterations. For each classifier used, we report the root-mean-square error (RMSE) in Table 2 to indicate the root mean square difference between predicted and observed values. The RMSE of each music sophistication trait relates to a [1,7] score scale.
|Valence std.dev||Track popularity std.dev|
|Tempo std.dev||Valence mean|
|Time signature mean||Valence median|
|Time signature std.dev||Valence max|
|Time signature min||Tempo std.dev|
|Liveness mean||Time signature std.dev|
|Liveness std.dev||Time signature min|
|Liveness median||Loudness median|
|Instrumentalness std.dev||Energy max|
|Energy std.dev||Danceability mean|
|Energy min||Danceability median|
We first trained a random forest classifier. Random forests have shown to have a reasonable performance when the features consist of high amounts of noise (Humston et al., 2010)
. As the random forest classifier failed to outperform the baseline in the emotions dimension, we used the RBF network classifier. The RBF network is a neural network that has shown to work well on smaller datasets(Khot et al., 2012).
|ZeroR||Random Forest||RBF network|
4. Conclusion, Limitations & Outlook
In this preliminary work we explored the prediction of musical sophistication subscales (i.e., emotions and active engagement) from music listening behavior. Our results show that music listening behavior can be used to infer the musical sophistication of users. We used a random forest classifier and an RBF network classifier to create the predictive models. Although both classifiers were able to outperform the baseline model on active engagement prediction, only the RBF network was able to also outperform the baseline on predicting the emotions subscale.
Although we were able to predict participants’ scores on two subscales of Gold-MSI from music listening behavior, performance can likely be improved more. To do this, we plan to extend the analysis in several ways. We aim to expand our dataset by increasing the number of participants in our dataset and the number of measurements per participant. This will allow for a more in-depth investigation of the relationship between behavioral features and the Gold-MSI scores. Furthermore, we plan to explore the prediction of other subscales of the Gold-MSI as well as exploring the predictive value of other music listening behaviors that are available through the Spotify API (e.g., user’s playlists and social networks).
We would like to thank Eelco Wiechert for creating the application.
- Celma (2010) Òscar Celma. 2010. Music Recommendation and Discovery. Springer Berlin Heidelberg, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13287-2
- Fernández-Tobías and Cantador (2015) Ignacio Fernández-Tobías and Iván Cantador. 2015. On the use of cross-domain user preferences and personality traits in collaborative filtering. In International Conference on User Modeling, Adaptation, and Personalization. Springer, 343–349.
Bruce Ferwerda and
Markus Schedl. 2016.
Personality-based user modeling for music
recommender systems. In
Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 254–257.
- Germanakos et al. (2016) Panagiotis Germanakos, Marios Belk, et al. 2016. Human-Centred Web Adaptation and Personalization. Springer.
- Graus et al. (2018) Mark P Graus, Martijn C Willemsen, and Chris CP Snijders. 2018. Personalizing an Online Parenting Library: Parenting-Style Surveys Outperform Behavioral Reading-Based Models. In The 23rd International on Intelligent User Interfaces.
- Hall et al. (2009) Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten. 2009. The WEKA Data Mining Software: An Update. SIGKDD Explor. Newsl. 11, 1 (Nov. 2009), 10–18. https://doi.org/10.1145/1656274.1656278
- Hauser et al. (2009) John R Hauser, Glen L Urban, Guilherme Liberali, and Michael Braun. 2009. Website morphing. Marketing Science 28, 2 (2009), 202–223.
- Humston et al. (2010) Elizabeth M Humston, Joshua D Knowles, Andrew McShea, and Robert E Synovec. 2010. Quantitative assessment of moisture damage for cacao bean quality using two-dimensional gas chromatography combined with time-of-flight mass spectrometry and chemometrics. Journal of Chromatography A 1217, 12 (2010).
- Khot et al. (2012) Lav R Khot, Suranjan Panigrahi, Curt Doetkott, Young Chang, Jacob Glower, Jayendra Amamcharla, Catherine Logue, and Julie Sherwood. 2012. Evaluation of technique to overcome small dataset problems during neural-network based contamination classification of packaged beef using integrated olfactory sensor system. LWT-Food Science and Technology (2012).
- Müllensiefen et al. (2014) Daniel Müllensiefen, Bruno Gingras, Jason Musil, and Lauren Stewart. 2014. The musicality of non-musicians: an index for assessing musical sophistication in the general population. PloS one 9, 2 (2014), e89642.