BBC-News_Topic-Modelling

project indentify the topics from the BBC news data.Its a python based Project and uses LDA(Latent Dirichlet Allocation) Algorithm for Topic Modelling. Data Contains various news feeds from BBC News which are then filtered and processed using various Python Packages such as NLTK, Genim and Spacy. However rather than using ntlk.stopwords i have use different file(extended_stopwords.txt), which contains extra set of words for removing stopwords from my data in preprocessing step. Further Details are mentione as comment or text in code .pynb file.