Computing Information Technology. The Human Side
Authors: Gordon S. R.
 Published year: 2003
 Pages: 25-27/186
Buy this book on amazon.com >>

Future Trends

The Self Organizing Map has great potential as a tool for creating useful visualizations of Websites. The present research has begun to develop the techniques necessary to get meaningful and useful results from the SOM neural network. In doing so, a visualization can be created that is as useful as the Web Usage Plot, but more robust in its computation. The SOM technique is relatively fast to compute, and has no restriction on the number of Web pages that can be considered .

However, there is still much more research necessary to successfully use the SOM as part of a professional visualization system. One difficulty in using the SOM is a problem with dealing with sparse data sets. In a small Website sample, it is quite possible that most of the Web pages are never visited, or are visited in one session. This means that of the hundreds of sessions available, a given Web page will have only a single column active. The SOM network will frequently overlook the subtle difference between such pages, in considering the vast similarity in their pattern of not being accessed in so many sessions. Finding a set of parameters and appropriate training regimen for dealing with this problem can be quite time consuming. At present, a variety of different parameters must be experimented with using trial and error in order to find a useful visualization.

Perhaps even more important than the enabling of intuitive visualizations, capturing a Website's usage pattern in a neural network could provide a remarkably versatile component in new Web-based applications. Recommendations could be made to the user on the fly, since when a user goes to a particular Web page, it will be clear which other pages the other users have visited from there. Also, it would be possible to recreate some user behaviors from the network itself, so that novel Website structures can be readily evaluated or compared.

Conclusions

For many businesses, the trail of data left by users visiting the company Website is an untapped resource. Each visit to the Website generates several lines in the Web log file, each of which has only a few pieces of relevant information. New tools are actively being developed to help Web professionals interpret this large, complex data set. The present research explores the application of a new tool, the self-organizing map neural network to the problem of Web usage mining.

The visualization of the self-organizing map presented here is unlike earlier work because it enables the interpretation of Website usage by individuals who do not have extensive training. Earlier Web usage mining procedures automate the analysis so that no human is involved (Mobasher et al., 2000), or use special data mining languages for interacting with the system (Spiliopoulou, 2000). By using the natural grouping of the self-organizing map, the present visualization allows an inexperienced individual to identify usage clusters, and to understand which pages are visited together frequently. Such a simple, specialized tool should enable a wide variety of practitioners to gain a better understanding of their Website users.

References

Kohonen, T., Kaski, S., Lagus, K., Salojrvi, J., Paatero, V., & Saarela, A. ( 2000 ). Self Organization of a Massive Document Collection. IEEE Transactions on Neural Networks , Special Issue on Neural Networks for Data Mining and Knowledge Discovery, 3 (11), 574–585.

Mobasher, B., Cooley, R., & Srivastava, J. ( 2000 ). Automatic Personalization Based on Web Usage Mining. Communications of the ACM , 43 (8).

Perotti, V., & Burke, A. ( 2001 ). The Visualization of Usage Patterns for Web Customization, Managing Information Technology in a Global Economy. Proceedings of the 2001 IRMA Conference . Toronto, Canada.

Spiliopoulou, M. ( 2000 ). Web Usage Mining for Web Site Evaluation. Communications of the ACM , 43 (8).

Computing Information Technology. The Human Side
Authors: Gordon S. R.
 Published year: 2003
 Pages: 25-27/186
Buy this book on amazon.com >>

Similar books