I tried doing text clustering using LDA, but it isn't giving me distinct clusters. Below is my code
#Import libraries
from gensim import corpora, models
import pandas as pd
from gensim.parsing.preprocessing import STOPWORDS
from itertools import chain
#stop words
stoplist = list(STOPWORDS)
new = ['education','certification','certificate','certified']
stoplist.extend(new)
stoplist.sort()
#read data
dat = pd.read_csv('D:\data_800k.csv',encoding='latin').Certi.tolist()
#remove stop words
texts = [[word for word in document.lower().split() if word not in stoplist] for document in dat]
#dictionary
dictionary = corpora.Dictionary(texts)
#corpus
corpus = [dictionary.doc2bow(text) for text in texts]
#train model
lda = models.LdaMulticore(corpus, id2word=dictionary, num_topics=25, workers=4,minimum_probability=0)
#print topics
lda.print_topics(num_topics=25, num_words=7)
#get corpus
lda_corpus = lda[corpus]
#calculate cutoff score
scores = list(chain(*[[score for topic_id,score in topic] \
for topic in [doc for doc in lda_corpus]]))
#threshold
threshold = sum(scores)/len(scores)
threshold
**0.039999999971137644**
#cluster1
cluster1 = [j for i,j in zip(lda_corpus,dat) if i[0][1] > threshold]
#cluster2
cluster2 = [j for i,j in zip(lda_corpus,dat) if i[1][1] > threshold]
The problem is there are overlapping elements in cluster1, which tend to be present in cluster2 and so on.
I also tried to increase threshold manually to 0.5, however it is giving me the same issue