02714nam a22001577a 4500999001700000100005000017245004600067260003000113300000700143500214800150700004302298856002602341942001102367952008802378952009002466  c55600d55597  aAdnan ManzooraSupervisor Dr. Asim Imad Wagan  aSentiment Analysis For Enterprise Mashup   aNawabshah:bQUEST,c2012.  a50  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.


  aDepartment of Information Technology    uhttp://tiny.cc/qbubvz  cTHESIS  00104070aRESEARCHbRESEARCHd2016-11-17l0pMP/01-8r2016-11-17 00:00:00yTHESIS  00104070aRESEARCHbRESEARCHd2018-10-09l0pMP/20-194r2018-10-09 00:00:00yTHESIS