NLP Analysis of wikipedia api
The purpose of this project is to use a prepared dataset of Wikipedia summaries in .csv format and explore them using Natural Language Processing (NLP) and the K-Nearest Neighbor analysis with the Tfidf transform to determine the ten nearest neighbors to a selected person in the summary .csv file.
In addition, a Wikipedia API must be used to access the full Wikipedia content of the Wikipedia pages for the selection person and their ten nearest neighbors.
Comparisons will be made of the nearest neighbors lists from the two sources, as well as of the sentiments of the Wiki summary and the Wikipedia full page for the targeted person.
An audience participation feature at the end will allow the audience to select a person and print the corresponding full text of the Wikipedia page using the Wikipedia API.