Exploiting crowd sourced reviews to explain movie recommendation

Sara El Aouad 1, 2, 3 Christophe Dupuy 4, 3 Renata Teixeira 1, 2 Christophe Diot 3 Francis Bach 4, 5
1 LINCS - Laboratory of Information, Network and Communication Sciences
2 MUSE - Measuring networks for enhancing USer Experience
Inria Paris-Rocquencourt
3 Technicolor R & I [Cesson Sévigné]
4 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
5 LIENS - Laboratoire d'informatique de l'école normale supérieure
Abstract : Streaming services such as Netflix, M-Go, and Hulu use advanced recommender systems to help their customers identify relevant content quickly and easily. These recommenders display the list of recommended movies organized in sublists labeled with the genre or some more specific labels. Unfortunately , existing methods to extract these labeled sublists require human annotators to manually label movies, which is time-consuming and biased by the views of annotators. In this paper, we design a method that relies on crowd sourced reviews to automatically identify groups of similar movies and label these groups. Our method takes the content of movie reviews available online as input for an algorithm based on Latent Dirichlet Allocation (LDA) that identifies groups of similar movies. We separate the set of similar movies that share the same combination of genre in sublists and personalize the movies to show in each sublist using matrix factorization. The results of a side-by-side comparison of our method against Technicolor's M-Go VoD service are encouraging.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download
https://hal.inria.fr/hal-01193308
Contributor : Sara El Aouad <>
Submitted on : Tuesday, September 22, 2015 - 2:37:46 PM
Last modification on : Wednesday, December 18, 2019 - 5:33:35 PM
Long-term archiving on: Monday, December 28, 2015 - 10:48:11 PM

File

shortPaperRecsys.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01193308, version 1

Collections

CNRS | INRIA | INSTITUT-TELECOM | UPMC | ENS-PARIS | PSL | SORBONNE-UNIVERSITE | SU-SCIENCES

Citation

Sara El Aouad, Christophe Dupuy, Renata Teixeira, Christophe Diot, Francis Bach. Exploiting crowd sourced reviews to explain movie recommendation. 2nd Workshop on Recommendation Systems for TELEVISION and ONLINE VIDEO, Sep 2015, Vienna, Austria. ⟨hal-01193308⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

1088

Files downloads

612

 

 

Contact

archive-ouverte@inria.fr