Website Classification Using Latent Dirichlet Allocation and Its Application for Internet Advertising

This study proposes a model for website classification using website content, and discusses applications for internet advertising (ad) strategies. Internet ad agencies have many ad-spaces embedded in many websites and can choose where to place advertisements. Therefore, ad agencies have to know the properties and topics of each website in order to optimize advertising submission strategy. However, since website content is in natural languages, they have to convert these qualitative sentences into quantitative data if they want to classify websites using statistical models. To address this issue, this study applies statistical analysis to website information written in natural languages. We apply a dictionary of neologisms in order to decompose website sentences into words and create a dataset of 0, 1 indicator matrices to classify the websites. From the dataset, we estimate the topics of each website using latent Dirichlet allocation. Finally, we discuss how to apply the results obtained to optimize ad strategies.