文件编号将如何影响Gensim LDA的结果？

Question

I use three txt file to do a LDA project I try to separate these three txt file with two way The difference among the process is:

docs = [[doc1.split(' ')], [doc2.split(' ')], [doc3.split(' ')]]
docs1 = [[''.join(i)] for i in re.split(r'\n{1,}', doc11)] + [[''.join(e)] for e in re.split(r'\n{1,}', doc22)] + [[''.join(t)] for t in re.split(r'\n{1,}', doc33)]    
dictionary = Dictionary(docs)
dictionary1 = Dictionary(docs1)
corpus = [dictionary.doc2bow(doc) for doc in docs]
corpus1 = [dictionary.doc2bow(doc) for doc in docs1]

And the document number is

len(corpus)
len(corpus1)
3
1329

But the lda model create a rubbish result in corpus but a relatively good result in corpus1

I use this model to train the document

model = gensim.models.ldamodel.LdaModel(corpus=corpus,
                                    id2word=id2word,
                                    num_topics=10, 
                                    random_state=100,
                                    update_every=1,
                                    chunksize=100,
                                    passes=10,
                                    alpha='auto',
                                    per_word_topics=True)

The difference in the two model is the document number, everything else is the same

Why LDA create such a different result in this two model?

Answer 1

If you study about LDA I think almost everywhere the first line is "LDA is good for large corpus whereas it doesn't work good for short text". In your corpus only 3 documents are there whereas in corpus1 it's 1329 so definitely it's gonna produce accurate results for corpus1

Another point is LDA works based on iterations and find random samples for training from documents, so when you have large corpus(more documents) it's most likely that every sample will be different as compared to same samples(few documents) and different samples can lead to more accurate results.

Hope this make sense.