Customer Reviews

Data Mining the Web: Uncovering Patterns in Web Content, Structure, and Usage

5 star:		(0)
4 star:		(0)
3 star:		(0)
2 star:		(1)
1 star:		(0)

 

 

I really wanted to like this book. I am an almost daily user of Clementine, which is featured in this book series. Also, while giving them mixed reviews, I like aspects of the first two books in the series. Most of all, Web Mining is an application area I would like to know more about. The two other books are Discovering Knowledge in Data: An Introduction to Data Mining and Data Mining Methods and Models

My review of this book will be more brief than my reviews of the other two because my main complaint is the topics that are absent. This book really assumes that you have at least the first book in the series. The modeling section is a mere 20 pages and cites the other books often. This is not merely an annoying detail. It prevents the authors from cleaning, preparing, and modeling a thorough and complete case study from start to finish. They have a good case study in the book, but there is much left to the imagination because modeling has already been covered in the other books. For instance, the section entitled "The application of the A priori algorithm to the web log data" is three pages.

Since I buy several related books a year, I got this largely based on my knowledge of the first book. It is not that it is badly written. (However, readers of the series will be able to tell which co-author wrote which section. The styles differ.) Rather, it is that it doesn't address topics that I was certain would be included regarding Clementine. I expected Text Mining and Sequence Analysis to make an appearance and they are not mentioned. For instance, what about text mining blogs? Actually, unlike the other two books, Clementine does not make a very frequent appearance in this book, probably around 15% of the material. Obviously, explicit references to Clementine are useful to me. If they are to you, you might be disappointed.

Unlike the other two books, some of the material in this book was new to me as I read it. I found it more difficult to follow. Is that because I have more experience with the topics in the other two books? Perhaps. I just can't recommend this to someone unless it is going to be part of a large collection on the subject.