Predicting sentiment of future tweet on twitter

4
votes

I'm trying to predict the sentiment of the next tweet posted by a twitter user. Right now I have the following steps (step 1 and 2 are already implemented in python):

  1. Learn how to classify a tweet as postive (1), neutral (0), or negative (-1). I use a naive bayes classifier for this and it works pretty well.

  2. Classify existing tweets from a user. This results in a series of numbers like this: [0, 1, -1, -1, -1, 0, 1, 1, ..] There's also information about the posting time.

Would it be possible to predict the sentiment (1, 0 or -1) for the next tweet?

What algorithm could I use for this?

I don't know how this one works yet, but are hidden markov models suitable or some kind of regression?

2
twittermachine-learningdata-miningclassification
One idea: Simply create another classifier that has as a feature the k-1 class label (what class was the immediately previous tweet), the k-2 class label, ..., and see if that is enough data to come up with a valid prediction. (My personal guess is that it is not enough, but we don't know unless you try.) Basically what you're doing is time series analysis. - Wesley Baugh
You can try to do so, but humans are usually not that easy to predict. The sentiment of the next tweet will likely not depend on the previous tweets a lot, but more on external factors that you do not observe in Twitter. When evaluating, be careful to not have bots in your data. - Has QUIT--Anony-Mousse

2 Answers

3
votes

I think one appealing way to think about this is in terms prior and likelihood for sentiment. Naive Bayes is a likelihood model (how probable am I to see this exact tweet, given that it's positive?). You're asking about the prior probability of a the next tweet being positive, given that you've observed a certain sequence of sentiments so far. There are a few ways you could do this:

  • The most naive way is the fraction of tweets the user has uttered which are positive is the probability that the next one will be positive
  • However, this ignores recency. You could come up with a transition-based model: from each possible previous state, there's a probability of the next tweet being positive, negative or neutral. Thus you have a 3x3 transition matrix, and the conditional probability of the next tweet being positive given the last one was positive is the transition probability pos->pos. This can be estimated from counts, and is a Markovian process (previous state is all that matters, basically).
  • You can get more and more complex with these transition models, for example the current 'state' could be the sentiments of the last two, or indeed last-n, tweets, meaning you get more specific predictions at the expense of more and more parameters in the model. You can overcome this with smoothing schemes, parameter tying etc. etc.

As a final point, I think @Anony-Mousse's point about the prior being weak evidence is going to be true: really, whatever your prior tells you, I think this is going to be dominated by the likelihood function (what's actually in the tweet in question). If you get to see the tweet as well, consider a CRF as @Neil McGuigan suggests.

0
votes

On the machine learning side, you could consider sequential associations:

http://web.mit.edu/rudin/www/RudinEtAlCOLT11.pdf

This site has some java libraries:

http://www.philippe-fournier-viger.com/spmf/

A Hidden Markov Model should also work. An HMM is a special case of a Conditional Random Field, which lets you look at other factors such as say weather or news events.

I wonder if the next tweet of a person is also affected by the current tweets of a) everyone b) or those that they follow