TY - GEN
T1 - Exploring a Topical Representation of Documents for Recommendation Systems
AU - Mendonça, Israel
AU - Trouvé, Antoine
AU - Fukuda, Akira
AU - Murakami, Kazuaki
N1 - Funding Information:
The authors are grateful to the National Council of Scientific and Technological Development (CNPQ) for its financial support through the Science Without Borders program, see (http://www.cienciasemfronteiras.gov.br).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10/31
Y1 - 2018/10/31
N2 - In this paper, we address the performance problems inherited when we use word embedding for recommendation. Free-text documents has no structural constructing rules, and are hard to model. Hence, the problem of having an accurate model, that conveys all the important information is a nontrivial problem. We convert the document to a numeric structure using word-embedding and test two document representations: one based in the center of this numeric representation and the other one based on pre-defined set of topics. We build a free text recommendation system and study how the performance, in terms of precision and recommendation time, is affected by both representations. We then vary the number of topics used to represent documents and verify the tradeoffs inherited from having a compact representation. The more compact the recommendation, the shorter the recommendation time, however more information is lost in the compactation process. We empirically test different possibilities for the topics and find an optimal point that is 3 times faster than a baseline and almost as accurate as it.
AB - In this paper, we address the performance problems inherited when we use word embedding for recommendation. Free-text documents has no structural constructing rules, and are hard to model. Hence, the problem of having an accurate model, that conveys all the important information is a nontrivial problem. We convert the document to a numeric structure using word-embedding and test two document representations: one based in the center of this numeric representation and the other one based on pre-defined set of topics. We build a free text recommendation system and study how the performance, in terms of precision and recommendation time, is affected by both representations. We then vary the number of topics used to represent documents and verify the tradeoffs inherited from having a compact representation. The more compact the recommendation, the shorter the recommendation time, however more information is lost in the compactation process. We empirically test different possibilities for the topics and find an optimal point that is 3 times faster than a baseline and almost as accurate as it.
UR - http://www.scopus.com/inward/record.url?scp=85057377941&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85057377941&partnerID=8YFLogxK
U2 - 10.1109/ICAwST.2018.8517192
DO - 10.1109/ICAwST.2018.8517192
M3 - Conference contribution
AN - SCOPUS:85057377941
T3 - 2018 9th International Conference on Awareness Science and Technology, iCAST 2018
SP - 73
EP - 78
BT - 2018 9th International Conference on Awareness Science and Technology, iCAST 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th International Conference on Awareness Science and Technology, iCAST 2018
Y2 - 19 September 2018 through 21 September 2018
ER -