Cross validation of neural network applications for automatic new topic identification

Abstract

AbstractThere are recent studies in the literature on automatic topic‐shift identification in Web search engine user sessions; however most of this work applied their topic‐shift identification algorithms on data logs from a single search engine. The purpose of this study is to provide the cross‐validation of an artificial neural network application to automatically identify topic changes in a web search engine user session by using data logs of different search engines for training and testing the neural network. Sample data logs from the Norwegian search engine FAST (currently owned by Overture) and Excite are used in this study. Findings of this study suggest that it could be possible to identify topic shifts and continuations successfully on a particular search engine user session using neural networks that are trained on a different search engine data log.