it is junk.
for what you want.
Tweets are supposed to persuade, communicate a message to entice someone to click.
Have to look for language patterns, not urls.
doc2vec allows one to assess semantic similarity.
mentions and urls are junk data, which you could use separately if you want.
For training you should strip them out.
So, if the same user is using multiple accounts, one still expects to see that similarity to persist across accounts. It is not about 100% accuracy here.
I am curious, how would you feel about a bot disseminating accurate, truthful information?
@phalexo With respect to my own opinions, or with the project I'm working on? In my opinion, such a bot would be fine and worthy of existence. With respect to my project, I'm not interested in detecting them (I'm focusing on foreign agents trying to spread misinformation or pretend to be American citizens)
@phalexo You could say that I'm technically interested in detecting fake accounts rather than fake people (since I understand that one person can run multiple fake accounts)
AttributeError: Can't get attribute 'DocvecsArray' on <module 'gensim.models.doc2vec' from '/anaconda3/lib/python3.6/site-packages/gensim/models/doc2vec.py'>
it seems to pop up when I'm trying to load a pretrained model from the following project: https://github.com/sb1992/NETL-Automatic-Topic-Labelling-
the gensim GitHub issue that I found seems to suggest that the error should've been fixed in a later version (I have the latest version of gensim currently)
any help would be greatly appreciated!
Did someone encountred this issue before ?
@eugines that's an interesting project! I was not aware of that. Tweeted it out now :)
Regarding your question: there has been some refactoring in the past 2-3 releases. We tried to maintain backward compatibility, but if NETL used some older version, there may have been an issue. @gojomo do you know whether the
DocvecsArray class moved (and where)?
If so, we should at least keep an alias in the old location, to maintain backward compatibility.
Do we have any convenience function (in gensim) for getting a word vector's length? (as a proxy for its frequency in the data the embedding was trained over)
Of course this question is motivated by laziness....
@phalexo thanks for being agressive though
Now ignoring your snarky comment, I'll post another question for others if they care to respond
I am probably not getting the point of
Don't people typically want to deal with sparse matrices in language processing? e.g. when training classification models over sparse language data; for example you typically can't efficiently train/fit a model on a large bag-of-wordish dense matrix in sklearn, without huge memory. What am I missing about it?
corpus2dense().Don't people typically want to deal with sparse matrices in language processing? e.g. when training classification models over sparse language data; for example you typically can't efficiently train/fit a model on a large bag-of-wordish dense matrix in sklearn, without huge memory. What am I missing about it?
Greetings chat, it's nice to have joined you. I have a relative simple question I suppose. I want to use tf-idf , executed the example in comments and successfully the code returned a vector with the index of the word and the probability, how can I map the index of that word to the actual word? is there a function I am not aware of ? Can I implement it somehow ?
@matanster for NumPy vectors , you can get their length using
vector.shape. See the # numpy vector of a word example at https://radimrehurek.com/gensim/models/keyedvectors.html#gensim.models.keyedvectors.KeyedVectors
@matanster regarding
corpus2dense: it's true NLP produces sparse matrices using the bag-of-words representation. But some later transformations, such as LSI, transform the sparse vectors into a dense space. So using a dense representation actually saves you memory (less overhead than representing a dense matrix using sparse structures).
Plus, there are many other external tools in the Data Science ecosystem that still cannot handle sparse inputs. So you have to export/supply a dense structure => need
corpus2dense. Even scikit-learn didn't have sparse support for a while ;)