|
Title:
|
BUILDING A KEYWORD-DRIVEN RECOMMENDER SYSTEM FOR ENTERTAINMENT VIDEOS WITH SIMPLE METADATA: A CASE STUDY |
|
Author(s):
|
Huan-Yu Lin, Jun-Ming Su, Yi-Li Liu, Shian-Shyong Tseng, Chin-Fu Hung, Hsiao-Wen Kao |
|
ISBN:
|
978-972-8939-23-6 |
|
Editors:
|
António Palma dos Reis and Ajith P. Abraham |
|
Year:
|
2010 |
|
Edition:
|
Single |
|
Keywords:
|
Although a recommender system is beneficial for sales of e-commerce, equipping the existing entertainment video webshops with recommenders directly is diff |
|
Type:
|
Poster / Demonstration |
|
First Page:
|
151 |
|
Last Page:
|
153 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Although a recommender system is beneficial for sales of e-commerce, equipping the existing entertainment video webshops with recommenders directly is difficult and time-consuming due to a huge amount of contents' simple metadata without sufficient semantic definitions. Therefore, in this paper, a Keyword-Driven Recommendation Scheme is proposed, which can automatically extract new keywords as features from content' simple metadata in Chinese based on keyword extraction heuristics and offer the personalized recommendation list based on heuristic-based recommendation strategy to avoid new item, and sparsity problems. The experimental results also show it is effective and beneficial. |
|
|
|
|
|
|
