Personality and Recommender Systems

Tkalčič, Marko; Chen, Li

doi:10.1007/978-1-4899-7637-6_21

Cited by 84 publications

(57 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several psychology-based studies have explored the relationship between personality traits and the types of the music people enjoy (Rentfrow & Gosling, 2003) and the manner in which music is consumed in everyday life (Chamorro-Premuzic & Furnham, 2007). Personality-based user modeling has also been proposed to improve recommender system performance (Onori, Micarelli, & Sansonetti, 2016;Braunhofer, Elahi, & Ricci, 2015;Braunhofer, Elahi, & Ricci, 2014;Hu & Pu, 2011; for a review, see Tkalcic & Chen, 2015). Onori et al (2016) explored methods of incorporating the Big Five personality traits into music recommender systems.…”

Section: Preference Characteristics In the Context Of Personalized Rementioning

confidence: 99%

Music discovery and revisiting behaviors of individuals with different preference characteristics: An experience sampling approach

Tang

Jhang

2019

Asso for Info Science & Tech

View full text Add to dashboard Cite

A mobile device‐enabled experience sampling study was conducted in which 44 participants answered questions about their music experiences 5 times a day for 2 weeks. Data regarding 4 aspects of their music‐related psychological traits—“music involvement,” “musical identity,” “preference diversity,” and “preference openness”—were also collected through a background questionnaire. A classification of music access modes was proposed based on the circumstances that lead to a music listening experience. A mixed regression analysis revealed several significant interaction effects between psychological traits and the mode of music access on music enjoyment. Foremost among these was a positive interaction effect between preference openness and the playing of a known track triggered by musical cues, and that between preference diversity and exposure to new music played by others. Individuals with a strong musical identity tended to enjoy music played of their own volition without any apparent triggers. Furthermore, a multimodal logistic regression analysis also revealed the relationships between these psychological traits and the likelihood of different music access modes. Preference diversity significantly increased the likelihood of music listening triggered by need arousal. The results support the proposition that users' music‐related psychological traits should be considered in personalized recommendation strategies.

show abstract

Section: Preference Characteristics In the Context Of Personalized Rementioning

confidence: 99%

Music discovery and revisiting behaviors of individuals with different preference characteristics: An experience sampling approach

Tang

Jhang

2019

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…One of the most influential models in psychology for studies encompassing personality and human behavior is the Five Factor Model (FFM), which characterizes Personality in terms of the five dimensions Openness, Conscientiousness, Extroversion, Agreeableness and Neuroticism [5,6,11,12,15,22]. Table 1 gives an overview of characteristics associated with each individual personality type [1,5,11,12,15,21,22].…”

Section: Background and Related Workmentioning

confidence: 99%

“…Hu et al [9] computed user similarity based on personality vectors and found that the personality-based algorithm resulted in better MAE, Recall and Specificity compared to the ratings-based one. Tkalcic and Chen [21] found that the personality-based approach generates more accurate recommendations than traditional ratings-based approach on a music dataset. Elahi et al [7] incorporated personality data, and found that their approach performed better than the random baseline method and the log(popularity)*entropy method in terms of MAE.…”

Section: Neuroticismmentioning

confidence: 99%

Exploring the Value of Personality in Predicting Rating Behaviors

Karumur

Nguyen

Konstan

2016

Proceedings of the 10th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

Prior work relevant to incorporating personality into recommender systems falls into two categories: social science studies and algorithmic ones. Social science studies of preference have found only small relationships between personality and category preferences, whereas, algorithmic approaches found a little improvement when incorporating personality into recommendations. As a result, despite good reasons to believe personality assessments should be useful in recommenders, we are left with no substantial demonstrated impact. In this work, we start with user data from a live recommender system, but study category-by-category variations in preference (both rating levels and distribution) across different personality types. By doing this, we hope to isolate specific areas where personality is most likely to provide value in recommender systems, while also modeling an analytic process that can be used in other domains. After controlling for the family-wise error rate, we find that High Agreeableness users rate at least 0.5 stars higher on a 5-star scale compared to low Agreeableness users. We also find differences in consumption in four different personality types between people who manifested high and low levels of that personality.

show abstract

“…and through different domains (e.g., movies, book, etc.) (Tkalcic and Chen 2015). A comprehensive and widely used personality model with respect to RSs is the Five-Factor Model, also known as the "Big Five" personality traits (Goldberg 1990).…”

Section: Introductionmentioning

confidence: 99%

What is the “Personality” of a tourism destination?

Sertkan

Neidhardt

Werthner

2018

Inf Technol Tourism

View full text Add to dashboard Cite

Researching online before booking a vacation can be seen as a common habit of customers nowadays. In this context, Recommender Systems (RSs) are aiming to support the customers to find the right products, but they face domain specific challenges since tourism products are typically very complex and related to emotional experiences. To counteract these challenges, comprehensive user models for capturing the preferences and personality of travellers have been introduced. One of these models is the so-called Seven-Factor Model. This paper introduces an automated way for determining the Seven-Factor representation of tourism destinations to enable a matchmaking for RSs. In particular, exploratory data analysis, cluster analysis, and regression analysis are conducted not only to find a mapping of destinations onto the Seven-Factors, but also to foster a better understanding of the relationship between destination attributes and the Seven-Factors. This work provides clear evidence that a tourism destination's Seven-Factor representation can be determined by taking its attributes into account. This is an extended version of a conference paper entitled "Mapping of tourism destinations to travel behavioural patterns" previously published in the proceedings

show abstract

Personality and Recommender Systems

Cited by 84 publications

References 54 publications

Music discovery and revisiting behaviors of individuals with different preference characteristics: An experience sampling approach

Music discovery and revisiting behaviors of individuals with different preference characteristics: An experience sampling approach

Exploring the Value of Personality in Predicting Rating Behaviors

What is the “Personality” of a tourism destination?

Contact Info

Product

Resources

About