Impact of Implicit and Explicit Affective Labeling on a Recommender System’s Performance

Tkalčič, Marko; Odi, Ante; Ko, Andrej; Tasič, J.F.

doi:10.1007/978-3-642-28509-7_32

Cited by 7 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each of the two approaches has its pros and cons. Again, Tkalcic et al [19] showed that content-based recommendation still works better when explicit labels are used, probably due to the still low accuracy of algorithms that detect affective responses. For this reason, research on improving affective implicit tagging is very active and opening up to a wide range of investigations.…”

Section: E E E P R O O Fmentioning

confidence: 99%

Affective Recommendation of Movies Based on Selected Connotative Features

Canini

Benini

Leonardi

2013

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

The apparent difficulty in assessing emotions elicited by movies and the undeniable high variability in subjects emotional responses to filmic content have been recently tackled by exploring film connotative properties: the set of shooting and editing conventions that help in transmitting meaning to the audience. Connotation provides an intermediate representation which exploits the objectivity of audiovisual descriptors to predict the subjective emotional reaction of single users. This is done without the need of registering users physiological signals neither by employing other people highly variable emotional rates, but just relying on the inter-subjectivity of connotative concepts and on the knowledge of users reactions to similar stimuli. This work extends previous by extracting audiovisual and film grammar descriptors and, driven by users rates on connotative properties, creates a shared framework where movie scenes are placed, compared and recommended according to connotation. We evaluate the potential of the proposed system by asking users to assess the ability of connotation in suggesting filmic content able to target their affective requests

show abstract

Section: E E E P R O O Fmentioning

confidence: 99%

Affective Recommendation of Movies Based on Selected Connotative Features

Canini

Benini

Leonardi

2013

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Throughout the last two decades, personalization became the core feature for the effectiveness of RS in a wide range of > REPLACE THIS LINE WITH YOUR MANUSCRIPT ID NUMBER (DOUBLE-CLICK HERE TO EDIT) < domains [7,32,40,41], with several trying to predict the users' preferences based on their personality [42][43][44][45][46][47][48][49]. Nunes, Cerri and Blanc [33] proposed the use of personality traits to recommend a president candidate for voters in the elections in France.…”

Section: B Personality-based Recommender Systemsmentioning

confidence: 99%

"You Want to Play a Game?" Detecting Personality Traits with Mobile Minigames

Alves,

Trindade,

Monteiro

et al. 2024

Preprint

View full text Add to dashboard Cite

The use of personality to improve recommendations is a growing trend in recommender systems. However, to accurately determine someone’s personality is complex, such as the need for long personality questionnaires which are subject to social desirability bias, or the need for a great amount of users’ interactions with the system. Also, most of the existing works focus on obtaining the broader personality dimensions instead of the more granular traits, which better characterize a person, and, so far, there are no shortduration mobile games that can accurately predict personality. In this work, we propose to implicitly acquire the users’ more granular personality traits, namely cautiousness and achievementstriving as a first concept proof, by using mobile short-duration serious games, in an attempt to also replace self-reporting personality questionnaires. A simulation with real participants (𝑛=100) was conducted. Several significant relationships with the proposed traits were found, although the sample size and social desirability bias found in the self-reporting personality questionnaire seemed to hinder the obtention of significant correlations. Interesting significant correlations with anger, modesty, friendliness, excitement seeking, cheerfulness, and adventurousness personality traits were also found. The results show mobile minigames are a viable way of unobtrusively determining the users’ more granular personality, being the path to replace personality questionnaires.

show abstract

“…Thus far we have focused on the implications of predictive algorithms based on one's own previous behavior. However, algorithms also serve content based on the prior behavior of similar others or people in general (Aggarwal, 2016;DiResta, 2020;Ricci et al, 2011;Tkalcic et al, 2009). For example, an in-depth analysis of Google search results suggests that they are both tailored to one's own prior search history as well as the search history of other users with a similar profile (Feuz et al, 2011).…”

Section: -314)mentioning

confidence: 99%

Freedom and Constraint in Digital Environments: Implications for the Self

Talaifar

Lowery

2022

Perspect Psychol Sci

View full text Add to dashboard Cite

We evaluate how features of the digital environment free or constrain the self. Based on the current empirical literature, we argue that modern technological features, such as predictive algorithms and tracking tools, pose four potential obstacles to the freedom of the self: lack of privacy and anonymity, (dis)embodiment and entrenchment of social hierarchy, changes to memory and cognition, and behavioral reinforcement coupled with reduced randomness. Comparing these constraints on the self to the freedom promised by earlier digital environments suggests that digital reality can be designed in more freeing ways. We describe how people reassert personal agency in the face of the digital environment’s constraints and provide avenues for future research regarding technology’s influence on the self.

show abstract

Impact of Implicit and Explicit Affective Labeling on a Recommender System’s Performance

Cited by 7 publications

References 23 publications

Affective Recommendation of Movies Based on Selected Connotative Features

Affective Recommendation of Movies Based on Selected Connotative Features

"You Want to Play a Game?" Detecting Personality Traits with Mobile Minigames

Freedom and Constraint in Digital Environments: Implications for the Self

Contact Info

Product

Resources

About