In this paper, we explore the effectiveness of using Zipf’s Law as a pre-processing step for classifying websites into four categories: Sports, Games & Toys, Travel, and Food & Drink. The classifiers used were Multinomial Logistic Regression and Convolutional Neural Network (CNN) using Global Vectors for Word Representation (GloVe) word embeddings. The CNN with GloVe embeddings as input produces 92% accuracy but increases to 93% when applying Zipf’s Law. The worst performing was the logistic regression with GloVe embeddings with accuracy of 90%. After we transformed our multi-class classification problem into a binary one, we saw a jump in accuracy. All models got an accuracy of 94% except for the base model (TF-IDF & LOGIT), which got a 93% accuracy.
All the code can be found on github.com.
|Commitee:||Zhang, Wenlu, VonBrecht, James|
|School:||California State University, Long Beach|
|Department:||Mathematics and Statistics|
|School Location:||United States -- California|
|Source:||MAI 81/4(E), Masters Abstracts International|
|Keywords:||Adtech, Deep Learning, Machine Learning, NLP, Zipf's Law|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be