Twitter Sentiment Analysis - BITS Pilani

Introduction

Used IFTTT to monitor twitter for the following keywords. #BITSPilani, #BITSGoa, #BITSHyd, #BITSDubai, #BITSAA, #BITS, #Pilani Obviously this has lot of noise as well due to 'BITS' keyword. Since IFTTT has stopped Twitter support for live searches, Use https://zapier.com/ and create your own dataset for analysis.

All the services will send you emails in one or the other formats, which is easy to parse. If you just have list of all tweets, Use twitter API to crawl the texts.

IFTTT Email format

ifttt

via task 618721:
http://ifttt.com/tasks/618721

Agam, the band, with BITSian roots http://t.co/EvIumdmJ http://twitter.com/BITSAA/status/166177110573064192
by http://twitter.com/BITSAA

Usage

1. Twitter training dataset taken from http://thinknook.com/twitter-sentiment-analysis-training-corpus-dataset-2012-09-22/ .
2. Parsed and formatted training datasets for 1.5M and .1M tweets has been included.
3. BITS Pilani Dataset containing tweets for the duration January 20, 2012 to September 27, 2012
4. Use Rapidminer 5.3 with -Xms2048m -Xmx3072m for faster calculations. Though other models are faster, SVM is really slow and so avoid using more than 0.1 Million dataset.

SVM model (~20 hours)

Performance Vector

	true 0	true 1	class precision
pred. 0	24042	9922	70.79%
pred. 1	19482	46537	70.49%
class recall	55.24%	82.43%

Stats

Top 10 Positive and Negative words

word	weight	word	weight
thank	0.06800427050495744	sad	0.06904954519705979
love	0.04238921785592977	miss	0.06799716497097386
good	0.03864780316342833	sorri	0.06447410364223946
great	0.03332699835307452	wish	0.04964308132602499
quot	0.028049576202737663	suck	0.04549754050714666
welcom	0.028045093611976712	bad	0.03882145370669514
awesom	0.027883840586310205	hate	0.038814744730334146
haha	0.027711586964757735	work	0.038456277249749565
nice	0.026502431781819224	poor	0.03537374379337165
happi	0.024842171425360552	want	0.03312521661076012

Sentiment Ratio

Positive Tweets	4759
Negative Tweets	1552

Naive Bayes (~4 hours)

Performance Vector

	true 0	true 1	class precision
pred. 0	34413	36884	48.27%
pred. 1	9111	19575	68.24%
class recall	79.07%	34.67%

Sentiment Ratio

Positive Tweets	3436
Negative Tweets	2875

License

MIT: http://vineetdhanawat.mit-license.org/