A Study of using web mining based personalization technology on web advertising
|
 |
|
Post a Comment
|
 |
|
|
|
|
ABSTRACT:
With the continuing growth of the population of Internet users, the market of Internet-based web advertising is also rapidly expanding. Since the web advertising is still an evolving new media, it is an important issue for the advertisers to understand and take the advantage of the web advertising over the traditional ways of advertising. Thus the establishment of an appropriate mechanism and operation model is essential to achieve better advertising effectiveness.
In this research, we first explore the present web advertising operating mechanism. Then we propose a personalized web advertising model based on web mining and user interestingness measurement. Three computational approaches for the extraction of user interestingness are suggested. We also use the clustering method to mine web users’ usage pattern and categorize each user into a relevant cluster for the delivery of the user’s “interested”
web advertisement. Based on this model, a prototype system was developed and several experiments were conducted using real web log data. Through the examination of the experimented results, we select evaluated the interestingness measurement method for this research. The user interestingness can be extracted without the user’s explicit participation. The extracted information can be utilized to deliver personalized web advertising services for each user. Under the web advertising operation model, all the three major participants of the web advertising will gain benefits respectively: the users receive personalized web advertisements unawarely; the advertisers
target their intended audience; and the advertising vendors improve their performance in bridging the advertisers and the potential customers, and competitive advantage.
|
|
|
|
STATISTICS
|
|
Click on # to view
|
|
Citations
|
|
0
|
|
References
|
|
0
|
|
Comments
|
|
0
|
|
Quality
|
|
0/0.00
|
|
Interest
|
|
0/0.00
|
|
View(er)s
|
|
2/785
|
|
|
|
|
|
|
| Prev |
Next |
|