|
Title:
|
PREDICTING THE SUCCESS OF POSTS FOR BRAND PAGES ON FACEBOOK |
|
Author(s):
|
Max-Emanuel Keller, Ben Stoffelen, Daniel Kailer, Peter Mandl and Jacqueline Althaller |
|
ISBN:
|
978-989-8533-82-1 |
|
Editors:
|
Pedro Isaías and Hans Weghorn |
|
Year:
|
2018 |
|
Edition:
|
Single |
|
Keywords:
|
Social Media, Social Networks, Facebook, Metrics, Prediction, Machine Learning |
|
Type:
|
Short Paper |
|
First Page:
|
349 |
|
Last Page:
|
354 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
The main contribution of this work in progress paper is a framework that assists a user to predict and evaluate the success of posts for brand pages on the social network Facebook. We propose a new approach that rates the success of a post either as successful or unsuccessful. It allows a user to create a new post and predict the expected success, even before publication. Posts that are considered unsuccessful can be further adjusted until the forecast becomes successful before they are published. But also posts already published can be evaluated according to their success. Finally, the forecast prepared prior to publication can be compared with the evaluation carried out after publication. We further demonstrate an early prototype that shows how an implementation could look like. Finally, we discuss some challenges for the proposed approach. |
|
|
|
|
|
|
