Standard
Forecasting audience increase on YouTube. /
Rowe, Matthew.
Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece. ed. / Fabian Abel; Qi Gao; Eelco Herder; Geert-Jan Houben; Daniel Olmedilla; Alexandre Passant. 2011.
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Rowe, M 2011,
Forecasting audience increase on YouTube. in F Abel, Q Gao, E Herder, G-J Houben, D Olmedilla & A Passant (eds),
Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece. User Profile Data on the Social Semantic Web (UWeb2011) Workshop, Extended Semantic Web Conference 2011, Greece,
30/05/11. <
http://www.wis.ewi.tudelft.nl/uweb2011/uweb2011-main-proceedings.pdf>
APA
Rowe, M. (2011).
Forecasting audience increase on YouTube. In F. Abel, Q. Gao, E. Herder, G-J. Houben, D. Olmedilla, & A. Passant (Eds.),
Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece http://www.wis.ewi.tudelft.nl/uweb2011/uweb2011-main-proceedings.pdf
Vancouver
Rowe M.
Forecasting audience increase on YouTube. In Abel F, Gao Q, Herder E, Houben G-J, Olmedilla D, Passant A, editors, Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece. 2011
Author
Rowe, Matthew. /
Forecasting audience increase on YouTube. Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece. editor / Fabian Abel ; Qi Gao ; Eelco Herder ; Geert-Jan Houben ; Daniel Olmedilla ; Alexandre Passant. 2011.
Bibtex
@inproceedings{1bceb0bd3b4a46eb969eaa466099bf6f,
title = "Forecasting audience increase on YouTube",
abstract = "User profiles constructed on Social Web platforms are often motivated by the need to maximise user reputation within a community.Subscriber, or follower, counts are an indicator of the influence and standingthat the user has, where greater values indicate a greater perception or regard for what the user has to say or share. However, at present there lacks an understanding of the factors that lead to an increase in such audience levels, and how a user{\textquoteright}s behaviour can affect their reputation. In this paper we attempt to fill this gap, by examining data collected from YouTube over regular time intervals. We explore the correlation between the subscriber counts and several behaviour features - extracted from both the user{\textquoteright}s profile and the content they have shared. Through the use of a Multiple Linear Regression model we are able to forecast the audience levels that users will yield based on observed behaviour. Combining such a model with an exhaustive feature selection process, we yieldstatistically significant performance over a baseline model containing allfeatures.",
keywords = "User modelling, Forecasting , Social Web , Data Mining , Behaviour",
author = "Matthew Rowe",
year = "2011",
month = may,
day = "30",
language = "English",
editor = "Abel, {Fabian } and Qi Gao and Eelco Herder and Geert-Jan Houben and Daniel Olmedilla and Alexandre Passant",
booktitle = "Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece",
note = "User Profile Data on the Social Semantic Web (UWeb2011) Workshop, Extended Semantic Web Conference 2011 ; Conference date: 30-05-2011",
}
RIS
TY - GEN
T1 - Forecasting audience increase on YouTube
AU - Rowe, Matthew
PY - 2011/5/30
Y1 - 2011/5/30
N2 - User profiles constructed on Social Web platforms are often motivated by the need to maximise user reputation within a community.Subscriber, or follower, counts are an indicator of the influence and standingthat the user has, where greater values indicate a greater perception or regard for what the user has to say or share. However, at present there lacks an understanding of the factors that lead to an increase in such audience levels, and how a user’s behaviour can affect their reputation. In this paper we attempt to fill this gap, by examining data collected from YouTube over regular time intervals. We explore the correlation between the subscriber counts and several behaviour features - extracted from both the user’s profile and the content they have shared. Through the use of a Multiple Linear Regression model we are able to forecast the audience levels that users will yield based on observed behaviour. Combining such a model with an exhaustive feature selection process, we yieldstatistically significant performance over a baseline model containing allfeatures.
AB - User profiles constructed on Social Web platforms are often motivated by the need to maximise user reputation within a community.Subscriber, or follower, counts are an indicator of the influence and standingthat the user has, where greater values indicate a greater perception or regard for what the user has to say or share. However, at present there lacks an understanding of the factors that lead to an increase in such audience levels, and how a user’s behaviour can affect their reputation. In this paper we attempt to fill this gap, by examining data collected from YouTube over regular time intervals. We explore the correlation between the subscriber counts and several behaviour features - extracted from both the user’s profile and the content they have shared. Through the use of a Multiple Linear Regression model we are able to forecast the audience levels that users will yield based on observed behaviour. Combining such a model with an exhaustive feature selection process, we yieldstatistically significant performance over a baseline model containing allfeatures.
KW - User modelling
KW - Forecasting
KW - Social Web
KW - Data Mining
KW - Behaviour
M3 - Conference contribution/Paper
BT - Proceedings of the International Workshop on User Profile Data on the Social Semantic Web co-located with 8th Extended Semantic Web Conference May 30, 2011, Heraklion, Crete, Greece
A2 - Abel, Fabian
A2 - Gao, Qi
A2 - Herder, Eelco
A2 - Houben, Geert-Jan
A2 - Olmedilla, Daniel
A2 - Passant, Alexandre
T2 - User Profile Data on the Social Semantic Web (UWeb2011) Workshop, Extended Semantic Web Conference 2011
Y2 - 30 May 2011
ER -
