Visualization of movie features in collaborative filtering

Bottyan Nemeth, Gabor Takacs, Istvan Pilaszy, D. Tikk

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

In this paper we will describe a modification of the matrix factorization (MF) algorithm which allows visualizing the user and item characteristics. When applying MF for collaborative filtering, we get a model that represents the attributes of users and items by feature vectors. Some elements of these vectors may have understandable meaning for humans but due to the lack of internal connections between the feature vectors, these are difficult to visualize. In this paper we give a detailed description of a MF method enabling better visualization of features by arranging them into a 2D map, where via the calculation of the feature values we try to position features with similar 'meaning' close to each other. To achieve this first we define a neighborhood relation on features, then we modify the MF so that we introduce a new term in the error function which penalize the difference between the neighbor features. We show that this modification slightly decrease the accuracy of the model but we get well visualized feature maps. On the feature maps meanings can be associated with regions, and so we can provide an interesting explanation for the user why he/she was recommended the movie. Such plausible explanations may result in that users will better understand how the system works, which can also increase customer loyalty towards the service provider.

Original languageEnglish
Title of host publicationSoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings
PublisherIEEE Computer Society
Pages229-233
Number of pages5
DOIs
Publication statusPublished - 2013
Event12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, SoMeT 2013 - Budapest, Hungary
Duration: Sep 22 2013Sep 24 2013

Other

Other12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, SoMeT 2013
CountryHungary
CityBudapest
Period9/22/139/24/13

Fingerprint

Collaborative filtering
Factorization
Visualization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Nemeth, B., Takacs, G., Pilaszy, I., & Tikk, D. (2013). Visualization of movie features in collaborative filtering. In SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings (pp. 229-233). [6645674] IEEE Computer Society. https://doi.org/10.1109/SoMeT.2013.6645674

Visualization of movie features in collaborative filtering. / Nemeth, Bottyan; Takacs, Gabor; Pilaszy, Istvan; Tikk, D.

SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings. IEEE Computer Society, 2013. p. 229-233 6645674.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nemeth, B, Takacs, G, Pilaszy, I & Tikk, D 2013, Visualization of movie features in collaborative filtering. in SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings., 6645674, IEEE Computer Society, pp. 229-233, 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, SoMeT 2013, Budapest, Hungary, 9/22/13. https://doi.org/10.1109/SoMeT.2013.6645674
Nemeth B, Takacs G, Pilaszy I, Tikk D. Visualization of movie features in collaborative filtering. In SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings. IEEE Computer Society. 2013. p. 229-233. 6645674 https://doi.org/10.1109/SoMeT.2013.6645674
Nemeth, Bottyan ; Takacs, Gabor ; Pilaszy, Istvan ; Tikk, D. / Visualization of movie features in collaborative filtering. SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings. IEEE Computer Society, 2013. pp. 229-233
@inproceedings{7ea102b6e94f40e39e1d177ffd8e2230,
title = "Visualization of movie features in collaborative filtering",
abstract = "In this paper we will describe a modification of the matrix factorization (MF) algorithm which allows visualizing the user and item characteristics. When applying MF for collaborative filtering, we get a model that represents the attributes of users and items by feature vectors. Some elements of these vectors may have understandable meaning for humans but due to the lack of internal connections between the feature vectors, these are difficult to visualize. In this paper we give a detailed description of a MF method enabling better visualization of features by arranging them into a 2D map, where via the calculation of the feature values we try to position features with similar 'meaning' close to each other. To achieve this first we define a neighborhood relation on features, then we modify the MF so that we introduce a new term in the error function which penalize the difference between the neighbor features. We show that this modification slightly decrease the accuracy of the model but we get well visualized feature maps. On the feature maps meanings can be associated with regions, and so we can provide an interesting explanation for the user why he/she was recommended the movie. Such plausible explanations may result in that users will better understand how the system works, which can also increase customer loyalty towards the service provider.",
author = "Bottyan Nemeth and Gabor Takacs and Istvan Pilaszy and D. Tikk",
year = "2013",
doi = "10.1109/SoMeT.2013.6645674",
language = "English",
pages = "229--233",
booktitle = "SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Visualization of movie features in collaborative filtering

AU - Nemeth, Bottyan

AU - Takacs, Gabor

AU - Pilaszy, Istvan

AU - Tikk, D.

PY - 2013

Y1 - 2013

N2 - In this paper we will describe a modification of the matrix factorization (MF) algorithm which allows visualizing the user and item characteristics. When applying MF for collaborative filtering, we get a model that represents the attributes of users and items by feature vectors. Some elements of these vectors may have understandable meaning for humans but due to the lack of internal connections between the feature vectors, these are difficult to visualize. In this paper we give a detailed description of a MF method enabling better visualization of features by arranging them into a 2D map, where via the calculation of the feature values we try to position features with similar 'meaning' close to each other. To achieve this first we define a neighborhood relation on features, then we modify the MF so that we introduce a new term in the error function which penalize the difference between the neighbor features. We show that this modification slightly decrease the accuracy of the model but we get well visualized feature maps. On the feature maps meanings can be associated with regions, and so we can provide an interesting explanation for the user why he/she was recommended the movie. Such plausible explanations may result in that users will better understand how the system works, which can also increase customer loyalty towards the service provider.

AB - In this paper we will describe a modification of the matrix factorization (MF) algorithm which allows visualizing the user and item characteristics. When applying MF for collaborative filtering, we get a model that represents the attributes of users and items by feature vectors. Some elements of these vectors may have understandable meaning for humans but due to the lack of internal connections between the feature vectors, these are difficult to visualize. In this paper we give a detailed description of a MF method enabling better visualization of features by arranging them into a 2D map, where via the calculation of the feature values we try to position features with similar 'meaning' close to each other. To achieve this first we define a neighborhood relation on features, then we modify the MF so that we introduce a new term in the error function which penalize the difference between the neighbor features. We show that this modification slightly decrease the accuracy of the model but we get well visualized feature maps. On the feature maps meanings can be associated with regions, and so we can provide an interesting explanation for the user why he/she was recommended the movie. Such plausible explanations may result in that users will better understand how the system works, which can also increase customer loyalty towards the service provider.

UR - http://www.scopus.com/inward/record.url?scp=84898612917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898612917&partnerID=8YFLogxK

U2 - 10.1109/SoMeT.2013.6645674

DO - 10.1109/SoMeT.2013.6645674

M3 - Conference contribution

AN - SCOPUS:84898612917

SP - 229

EP - 233

BT - SoMeT 2013 - 12th IEEE International Conference on Intelligent Software Methodologies, Tools and Techniques, Proceedings

PB - IEEE Computer Society

ER -