Please use this identifier to cite or link to this item:
Title: Can machines learn questions?
Authors: Soo, Alvin
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2018
Abstract: Analyzing information is crucial for businesses these days with many looking to reviews and feedbacks for areas of improvement. There is a need to sort the information gathered so that it can be processed easily and therefore an automatic document classifier is built. The two algorithms used to build the classifier are Latent Dirichlet Allocation and Extreme Learning Machine. To ensure the highest performance of the classifier, the dataset is pre-processed in different ways and tested to check its performance. Text pre-processing includes removal of common stop words, punctuation and numerical numbers. Through the different tests and experiments, the parameters that performed the best can be chosen and used to work on other datasets for further testing.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.31 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 18, 2024


Updated on Jun 18, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.