Search or add a thesis

Advanced Search (Beta)
Home > Comparative Analysis of Sentiment Analysis Techniques for Social Media

Comparative Analysis of Sentiment Analysis Techniques for Social Media

Thesis Info

Access Option

External Link

Author

Maria Hamid

Institute

Virtual University of Pakistan

Institute Type

Public

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2017

Thesis Completion Status

Completed

Subject

Software Engineering

Language

English

Link

http://vspace.vu.edu.pk/detail.aspx?id=118

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676720971079

Similar


Nowadays the excessive use of internet produces a huge amount of data due to the social networks such as Twitter, Facebook, Orkut and Tumbler. These are microblogging sites and are used to share the people opinions and suggestions on daily basis relevant to the certain topic. These are beneficial for decision making or extracting conclusions. Analysis of these feeds aims to assess the thinking and comments of people about some personality or topic. Sentiment analysis is a type of text classification and is performed by various techniques such as Machine Learning Techniques and shows that the text is negative, positive or neutral. In this work, we provide a comparison of most recent sentiment analysis techniques such as Na?ve Bayes, Bagging, Random Forest, Decision Tree, Support Vector Machine and Maximum entropy. The purpose of the study is to provide an empirical analysis of existing classification techniques for social media for analyzing the good performance and better information retrieval. A comprehensive comparative framework is designed to compare these techniques. Various benchmark datasets (UCI, KAGGLE) available in different repositories are used for comparison purpose. We presented an empirical analysis of six classifiers. The analysis results that Random Forest performs much better as compared to other. Efforts are made to provide a conclusion about different algorithms based on numerical and graphical metrics to conclude that which algorithm is optimal.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

خرگوش تے گدڑ

خرگوش تے گدڑ

اک سی خرگوش تے اک سی گدڑ۔ خرگوش گدڑ دا ماما سی۔ دونواں نے اک اک بیری دا رکھ لایا۔ خرگوش اپنی بیری نوں ویلے سر پانی دیندا، دوجے جانوراں توں راکھی کردا تاں جے اوہ ایس نوں کھا نہ جاون۔ گدڑ اپنی بیری ولوں اوناں ای لاپرواہ سی۔ کدے کدے پانی دیندا۔ اوہ وی گندی نالی دا۔ کجھ دناں دے بعد دوہاں دیاں بیریاں وڈیاں ہو گئیاں۔خرگوش دی بیری نوں مٹھے تے گدڑ دی بیری نوں کوڑے بیر لگدے سن۔ جدوں گدڑ نے بیر کھانے ہوندے تاں اوہ خرگوش کولوں منگ لیندا۔ اسرے بیر کھا کے اوہ ہور بیر منگدا تاں خرگوش آکھدا بس بس، سواد پے جاؤ گا۔

اک دن خرگوش تے گدڑ بازار گئے اور ویکھیا کہ اک دکان تے اوہدا مالک موجود نہیں۔ اوہ دونویں دکان اندر وڑ جاندے نیں۔ خرگوش آپ کھنڈ دی بوری اتے بہہ کے مزے نال کھنڈ کھاندا رہندا اے۔ گدڑ نوں اوہ مر چاں والی بوری اتے بہا دیندا اے۔ گدڑ نوں جدوں مرچاں چڑھ دیا نیں تاں اوہ خرگوش کولوں کھنڈ کھاون نوں منگدا اے۔ خرگوش اوہنوں آکھدا اے کہ چپ کر جا۔ تیری آواز سن کے دکان دار نہ آ جاوے۔ اپنے چرنوں دکان دار آ جاندا اے۔ خرگوش چھیتی نال اوتھوں نس جاندا اے تے گدڑ دکان دار دے قابو آ جاندا اے۔ شام نوں اوہ گدڑ نوں اپنے گھر لیا کے بنھ لیندا اے۔ اوہ گدڑ نوں کھاون نوں سکی روٹیاں تے پین نوں گرم پانی دیندا ٓے۔ ایس پاروں گدڑ بہت ماڑا ہو گیا۔

کجھ دناں بعد اوس نوں کسے دوسرے شہر کم لئی جانا پیندا اے۔ اوہ اپنی گھر والی نوں آکھدا اے کہ گدڑ نوں سکی روٹی دینی اے تے پین لئی گرم پانی۔ اوہدے گھر والی بولی ہوندی...

Customer-Focused Supply Chain Strategy Developing 4 Rs Model in Apparel Industry

In CFSCS the chief achievement is to counter consumer demand in real-time, that act will cut down the cost to experience productivity at an economical scale and give a chance to customers to practice a superior experience. The organizations practicing or implementing a strong CFSCS (customer-focused supply chain strategy) are performing at their excellence in the sales sector, share in the market, productivity, and high level of customer satisfaction. The supply chain mechanism is highly customer focused in CFSCS, Chief elements of the success are highly dependent on the 4Rs model (responsiveness, resiliency, reliability, and realignment) and provide better services at low cost as compared to the traditional supply chain model. The study explores that the 4Rs model in CFSCS is a chief driver for this purpose we develop various frameworks. Our field of proving the CFSCS 4Rs model is in the apparel industry.

Studies on Development of Corrosion Resistant Coatings for Preservation of Marine Installations With Emphasis to Karachi Coastal Area Conditons

Atmospheric corrosion near the coastal areas of Karachi is an active area of research. This research in this thesis aimed at studying Karachi’s coastal area conditions and the development of effective corrosion-resistant coatings. In the first step, atmospheric corrosivity was determined according to the ISO 9223 standard, which is a function of four factors: corrosion rate (rcorr), air salinity and SO2 pollution and time of wetness (TOW). For this purpose, mild steel and electrogalvanized mild steel test coupons were exposed over a period of 24 months from May 2014 to May 2016 at two atmospheric corrosion stations, located in National Institute of Oceanography (NIO) and Karachi Port Trust (KPT) along the coastal line of Karachi, Pakistan. Characterization of the corrosion products after one-year and two-year was done by scanning electron microscopy/energy dispersive X-ray spectroscopy, Fourier transform infrared spectroscopy and X-ray diffraction. Results showed that the corrosion rates of mild steel are high on both sites, but the corrosivity found at NIO is higher (C5) than in KPT (C4). It was also found that by using electrogalvanized mild steel the corrosivity obtained for NIO (C5+) and KPT (C5+) was not in agreement with the corrosivity category (C5) established by using the pollution category and TOW. The second part of this study focused on the development of corrosion-resistant coatings by the incorporation of titanium and aluminum metal powders to an epoxy resin. The film hardness measurement by pencil test, adhesion measurement by the cross hatch and tape test, chemical and heat resistance test, water sorption test, natural exposure and salt spray testing all demonstrated that developed titanium and aluminum metal powder based corrosion resistant coatings were better as compared to the commercially available epoxy coating. Failure analysis of the developed titanium and aluminum metal powder based corrosion resistant coatings was carried out by scanning electron microscopy (SEM) and Fourier transform infrared (FTIR) spectroscopy. Gloss measurement for all the coated test coupons was done. It was found that titanium metal powder based epoxy coating was better than aluminum metal powder based and commercially available epoxy coatings. Present research can be extended for the modification of other resins.