000			02525nam a22001337a 4500
999			_c55600 _d55597
100			_aAdnan Manzoor _aSupervisor Dr. Asim Imad Wagan
245			_aSentiment Analysis For Enterprise Mashup
260			_aNawabshah: _bQUEST, _c2012.
300			_a50
500			_aABSTRACT It is a human nature to ask for suggestion. When someone busy something. Need help to. find good restaurant, which politician to vote for, where to go to get the best out of autumn drive. People always need the advice of their friends and family to choose the best things among the possible options. Before the World Wide Web (WWW) entered into our lives, people used to ask their friends to recommend them before buying a product or where to visit. Web 2.0 has provided many platforms: blogs, microblogs, social networks which provide researchers many opportunities to manipulate the massive amount of information available on the WWW for intelligent purposes. There are many dimensions in which the information available on social networking sites can be used. Such as, if you are planning to invest on a stock then it could be interested to look for the latest news and reviews about that stock on Twitter Facebook or Google+ to see what people's opinions are about the stock or company. There is a need to process this huge volume of data automatically and find the hidden patterns in those reviews and news. The main objective of our research is to find the covert sentiments in Twitter status messages which can help companies to realize the true potential of their businesses and can also help individuals to make better decision during a purchase. The status messages (tweets) are extracted from twitter about different companies, products, and personalities and analyze what are people 's opinions (positive or negative) about those entities? The data is extracted using twitter API. A framework is proposed which facilitates to test different techniques and find the one which works best with polarity detection of twitter messages. Bigram, unigram, and term frequency and inverse document frequency (TF-IDF) and other feature selection methods are used along with three machine learning algorithn1s, support vector machines, stochastic decent gradient, and Naive Bayes. The work also includes performance comparison of different learning methods to analyze which kinds of techniques work best with twitter corpus.
700			_aDepartment of Information Technology
856			_uhttp://tiny.cc/qbubvz
942			_cTHESIS