Presentation 2021-12-17
Evaluating Prediction of the Access Counts of Videos Using Metadata as a Learning Parameter
Gen Koujitani, Masaya Nakayama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to predict the number of accesses to videos posted on video sharing services, we performed regression prediction using a multilayer perceptron using metadata based on several factors that are thought to influence the number of accesses. In this study, we used metadata such as tags and titles as explanatory variables to predict the number of accesses to a video without preprocessing such as clustering. The accuracy of the regression prediction was compared between the conditions of the proposed method and the conditions of a pseudo-reproduction of the previous study's method, which required clustering, and it was confirmed that the conditions of the proposed method were superior to those of the previous study regardless of whether clustering was used or not.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / regression prediction / multilayer perceptron / video-sharing service / Nico Nico Douga
Paper # IA2021-47
Date of Issue 2021-12-09 (IA)

Conference Information
Committee IN / IA
Conference Date 2021/12/16(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Higashi-Senda campus, Hiroshima Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Performance Analysis and Simulation, Robustness, Traffic and Throughput Measurement, Quality of Service (QoS) Control, Congestion Control, Overlay Network/P2P, IPv6, Multicast, Routing, DDoS, etc.
Chair Kenji Ishida(Hiroshima City Univ.) / Tomoki Yoshihisa(Osaka Univ.)
Vice Chair Kunio Hato(Internet Multifeed) / Toru Kondo(Hiroshima Univ.) / Yuichiro Hei(KDDI Research) / Hiroshi Yamamoto(Ritsumeikan Univ.)
Secretary Kunio Hato(NTT) / Toru Kondo(Univ. of Nagasaki) / Yuichiro Hei(Nagaoka Univ. of Tech.) / Hiroshi Yamamoto(KDDI Research)
Assistant / Daisuke Kotani(Kyoto Univ.) / Ryo Nakamurai(Fukuoka Univ.) / Daiki Nobayashi(Kyushu Inst. of Tech.)

Paper Information
Registration To Technical Committee on Information Networks / Technical Committee on Internet Architecture
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluating Prediction of the Access Counts of Videos Using Metadata as a Learning Parameter
Sub Title (in English)
Keyword(1) neural network
Keyword(2) regression prediction
Keyword(3) multilayer perceptron
Keyword(4) video-sharing service
Keyword(5) Nico Nico Douga
1st Author's Name Gen Koujitani
1st Author's Affiliation The University of Tokyo(Univ. Tokyo)
2nd Author's Name Masaya Nakayama
2nd Author's Affiliation The University of Tokyo(Univ. Tokyo)
Date 2021-12-17
Paper # IA2021-47
Volume (vol) vol.121
Number (no) IA-300
Page pp.pp.77-84(IA),
#Pages 8
Date of Issue 2021-12-09 (IA)