public static void HashtagRetweetProcessor()
{
var context = new OclumenContext();
var localUnprocessedHashtags = new Queue <string>();
var localUnprocessedRetweets = new Queue <string>();
int sleepTime = AppConfigSettings.ProcessTweetThreadSleepTime;
while (CrawlerStatus.KeepRunning)
{
// grab from the producer queue and put into our own local consumer queue
lock (_syncRoot)
{
while (UnprocessedHashtags.Count != 0)
{
localUnprocessedHashtags.Enqueue(UnprocessedHashtags.Dequeue());
}
while (UnprocessedRetweets.Count != 0)
{
localUnprocessedRetweets.Enqueue(UnprocessedRetweets.Dequeue());
}
}
// if we didnt get anything from either queue, sleep for a bit
if (localUnprocessedHashtags.Count == 0 && localUnprocessedRetweets.Count == 0)
{
Thread.Sleep(sleepTime);
continue;
}
var now = DateTime.UtcNow;
// ok, lets add the recently acquired data to our dataset
while (localUnprocessedHashtags.Count != 0)
{
context.HashtagUseRecords.Add(new HashtagUseRecord()
{
Tag = localUnprocessedHashtags.Dequeue(),
Timestamp = now
});
}
while (localUnprocessedRetweets.Count != 0)
{
var currentRetweet = localUnprocessedRetweets.Dequeue();
//remove preceding :
if (currentRetweet.Length >= 1 && currentRetweet.Substring(0, 1) == ":")
{
currentRetweet = currentRetweet.Substring(1, currentRetweet.Length - 1).Trim();
}
// remove any proceding rt
if (currentRetweet.Length >= 3 && currentRetweet.Substring(0, 3) == "RT ")
{
currentRetweet = currentRetweet.Substring(3, currentRetweet.Length - 3).Trim();
}
// sometimes the rt function produces an empty string with just : so we might want to skip that
if (currentRetweet != String.Empty)
{
context.RetweetUseRecords.Add(new RetweetUseRecord()
{
Tag = currentRetweet,
Timestamp = now
});
}
}
context.SaveChanges();
}
}
public static void TweetClassifier()
{
var context = new OclumenContext();
var classifier = new NaiveBayes();
var smoothingFactor = 1;
var unigrams = new Dictionary <string, List <KeyValuePair <Sentiment, decimal> > >();
var unigramsSt = new Dictionary <string, List <KeyValuePair <Sentiment, decimal> > >();
var bigrams = new Dictionary <string, List <KeyValuePair <Sentiment, decimal> > >();
var bigramsSt = new Dictionary <string, List <KeyValuePair <Sentiment, decimal> > >();
foreach (var ngram in context.BasicNgrams.Where(x => x.Cardinality == 1))
{
var ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.PositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.NeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.NegativeCount + smoothingFactor));
unigrams.Add(ngram.Text.ToLower(), ngramProbabilityList);
ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.RtPositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.RtNeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.RtNegativeCount + smoothingFactor));
unigrams.Add(ngram.Text.ToLower() + "_rt", ngramProbabilityList);
}
foreach (var ngram in context.StemmedNgrams.Where(x => x.Cardinality == 1))
{
var ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.PositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.NeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.NegativeCount + smoothingFactor));
unigramsSt.Add(ngram.Text.ToLower(), ngramProbabilityList);
ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.RtPositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.RtNeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.RtNegativeCount + smoothingFactor));
unigramsSt.Add(ngram.Text.ToLower() + "_rt", ngramProbabilityList);
}
foreach (var ngram in context.BasicNgrams.Where(x => x.Cardinality == 2))
{
var ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.PositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.NeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.NegativeCount + smoothingFactor));
bigrams.Add(ngram.Text.ToLower(), ngramProbabilityList);
ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.RtPositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.RtNeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.RtNegativeCount + smoothingFactor));
bigrams.Add(ngram.Text.ToLower() + "_rt", ngramProbabilityList);
}
foreach (var ngram in context.StemmedNgrams.Where(x => x.Cardinality == 2))
{
var ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.PositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.NeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.NegativeCount + smoothingFactor));
bigramsSt.Add(ngram.Text.ToLower(), ngramProbabilityList);
ngramProbabilityList = new List <KeyValuePair <Sentiment, decimal> >(3);
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Positive, ngram.RtPositiveCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Neutral, ngram.RtNeutralCount + smoothingFactor));
ngramProbabilityList.Add(new KeyValuePair <Sentiment, decimal>(Sentiment.Negative, ngram.RtNegativeCount + smoothingFactor));
bigramsSt.Add(ngram.Text.ToLower() + "_rt", ngramProbabilityList);
}
int sleepTime = AppConfigSettings.ProcessTweetThreadSleepTime;
while (CrawlerStatus.KeepRunning)
{
var tweetToProcess = context.RawTweets.First(x => x.AutoSentimentTimestamp == DateTime.MinValue);
if (tweetToProcess == null)
{
Thread.Sleep(sleepTime);
continue;
}
// add the hashtags to process queue
String originalTweet;
var hashtags = TwitterTextUtility.GetHashtags(tweetToProcess.text);
var retweets = TwitterTextUtility.GetRetweets(tweetToProcess.text, out originalTweet);
lock (_syncRoot)
{
foreach (var hashtag in hashtags)
{
UnprocessedHashtags.Enqueue(hashtag);
}
foreach (var retweet in retweets)
{
UnprocessedRetweets.Enqueue(retweet);
}
}
// auto classify the tweets
tweetToProcess.AutoUnigram = (int)classifier.GetTextSentiment(tweetToProcess.text, 1, 1, false, Dictionary, context.BasicNgrams, context, unigrams);
tweetToProcess.AutoUnigramStemmed = (int)classifier.GetTextSentiment(tweetToProcess.text, 1, 1, true, Dictionary, context.StemmedNgrams, context, unigramsSt);
tweetToProcess.AutoBigram = (int)classifier.GetTextSentiment(tweetToProcess.text, 2, 1, false, Dictionary, context.BasicNgrams, context, bigrams);
tweetToProcess.AutoBigramStemmed = (int)classifier.GetTextSentiment(tweetToProcess.text, 2, 1, true, Dictionary, context.StemmedNgrams, context, bigramsSt);
tweetToProcess.AutoSentimentTimestamp = DateTime.UtcNow;
context.SaveChanges();
}
}
