Year: 2018
Type: article
Abstract: Growing competition over the years has seen an increase in getting vital information like customer behaviour, his likes and dislikes before launching a product. Extracting the information from a huge pool of data like internet is what we in technical terms know as Web Mining (WM). With the technology comes the challenges too and getting correct information from a very large pool of data is always a big task. Traditionally WM uses content, structure and usage mining techniques but still the user sometime is not able to retrieve what he is looking for. Proper filtering of the information retrieved in the form of text or in other words text mining could make a lot of difference between correct information and lot of information. The paper focuses on digging the web to create a comprehensive repository for web miners looking for e-learning. 2000 URLs related with different online learning were taken into consideration, the information was read using python and raw text was collected. Python’s punctuation and itemgetter modules were used to retain only the major keywords having counts over a threshold, after performing basic text mining techniques. To check the robustness of the retained data precision, recall and accuracy was calculated and it was found that the precision, recall and accuracy were 0.964, 0.982 and 0.97 respectively.
Authors: Kamika Chaudhary, Neena Gupta
Language: English
Topic: Web Data Mining and Analysis
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W2884282854
