Search or add a thesis

Advanced Search (Beta)
Home > A Robust Framework of Sentiment Analysis for Online Customer Reviews and Blogs

A Robust Framework of Sentiment Analysis for Online Customer Reviews and Blogs

Thesis Info

Access Option

External Link

Author

Khan, Fazal Masud

Program

PhD

Institute

Gomal University

City

Dera Ismail Khan

Province

KPK

Country

Pakistan

Thesis Completing Year

2015

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/6657/1/Fazal_Masud_Khan_2015_Computer_Sciece_Gomal_Univ_DIK.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727687658

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


The Web 2.0 has dramatically changed people‟s communication style. It is a great move toward more community oriented, highly collaborative, interactive and responsive Web. Today we are not only using the Internet but we are part of this global network. Social media sites became the world‟s largest virtual community, where people express their views about products, events and services, anytime from anywhere. These views have great impact on community thinking and decisions. The most flourished feature of this era is the rising of blogging which provides resourceful and open way to anyone, anywhere. These data sources provide the rich basis for sentiment analysis. The statistics show that 80% of consumers have changed their decisions about purchase based on negative reviews found online. The study found that blogs are 63% more likely to influence purchase decisions than magazines. Evaluation of social media has powered interest in sentiment analysis. There exist two main approaches for extracting sentiment automatically, the lexicon-based approach and statistical or machine learning approach. The later approach demands a lot of training data to learn lexical items that express sentiment and its performance drops when the same classifiers is used in a different domain. The main focus of this work is to develop a lexicon-based framework for automatic classification of blogs and reviews with respect to their semantic orientation. This method consists of three major components: Sentiment analysis, Slang‟s detection and scoring, and Context-aware spelling corrector. Lexicon-based methods for sentiment analysis are robust, give good performance in cross-domain and can be easily boosted with additional source of knowledge. It performs well on blog posting, reviews and also a preferable classifier for handling contextual valence shifters. Irrespective of these merits no single lexicon can perform in an optimal way all the time. This method uses a dynamic, updateable and comprehensive lexicon based on existing opinion lexicons, dictionaries and other machine-readable resources to classify the user-generated contents into positive, negative and neutral polarity. vii Slangs and spelling correction are two vital elements for sentiment analysis because slang and misspelled word may affect the sentiment score. These two issues were handled using Web resources and Statistical language model. The proposed work was implemented, and evaluated with different datasets of reviews and blogs. The empirical results show that the proposed work outperforms the existing, related methods and achieves 90.3% accuracy on average. This method showed high accuracy in binary classification. All the three components of the proposed method performed well with different domains.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

چاک دامان لیے، چاک گریبان لیے

چاک دامان لیے، چاک گریبان لیے
محفلِ قیس میں پہنچے ہیں یہ سامان لیے

آئے تھے دنیا میں ارمانوں کو پورا کرنے
جائیں گے یاں سے مگر لاکھوں ہی ارمان لیے

لوگ کہتے ہیں جو دیوانہ ہمیں، کہنے دو!
ہم بھی نازاں ہیں کہ زندہ ہیں یہ پہچان لیے

جب کسی سے بھی مرے درد کا درماں نہ ہوا
آ گئی موت مرے درد کا درمان لیے

موسمِ گل ہو خزاں ہو، کہ بہاریں تائبؔ
اپنی تو ذات میں ہم پھرتے ہیں زندان لیے

سیاسی اضطرابی صورتحال کا جائزہ اور اس کا حل: سیرۃ نبویﷺ کی روشنی میں

Pakistan is an Ideological country, there are only two ideological states in the world. First one was Madinah (Saudi Arabia) and the second one is Pakistan. Political situation in our country is worst. There is no any stability in political situation. From its existence Pakistan is facing different problems and issues. In this research article, will try to draw reasons and will table solutions to get political stability in Pakistan.

Effect of Toxic Gases and Seasonal Variation in Plants Leaves and Stomata, a Case Study of Quetta City

Ambient status of Quetta city was estimated by recorded the contents of air pollutants viz. CO, NO2, SO2, SPM10μm and SPM2.5μm from its atmosphere. Statistical analysis using t-test indicated that all the seasonally investigated air pollutants were significant high at Quetta city (polluted sites) than control sites at the significant level of P<0.01. The concentration of all the pollutants start increasing slightly from spring to summer and reached to its maximum during autumn and lowest was found in the winter. Correlation Coefficient and Linear relationship indicated that all the air pollutants were highly, positively and significantly correlated with the number of vehicles movement. Air Quality Index of Quetta city revealed that the atmosphere of city is harmful for people of sensitive group and particularly the contents of particulate matters (SPM10μm and SPM2.5μm) are more than permissible level. Statistical analysis of all estimated heavy metals (Pb, Zn, Fe, Cu, Cd and Sb) exhibited that these were found slightly (P<0.05) to highly (P<0.01) significant high from the polluted sites plant species of Quetta city as compare to the control sites. Air pollution effects on biochemical and physiological attributes of plants leaves was determined by analysis of ascorbic acid content (AAC), total leaf chlorophyll content (TLC), leaf-extract pH and leaf relative water content (RWC). Statistical analysis indicated that all measured attributes in plant leaf showed slightly (P<0.05) to highly (P<0.01) significant variation between polluted and non-polluted sites. Air Pollution Tolerance Index (APTI) of different plant species exhibited that the overall APTI was significant in polluted site plants than those of non-polluted sites. On the basis of APTI, out of 14 plant species only two species, Eucalyptus tereticornis L. and Pinus halepensis Miller. were found to be highly Tolerant (T), other five plants i.e. Fraxinus excelsior L., Robinia pseudoacacia L., Punica granatum L., Prunus armeniaca L. and Elaeagnus angustifolia L. were moderately tolerant (MT) while other five species viz. Pistacia vera L., Rosa indica L., Melia azadirach L., Morus nigra L. and Ficus carica L. were Intermediately tolerant (IT), where as remaining two species Morus alba L. and Vitis vinifera L. were Sensitive (S). Effect of air pollution on morphological characteristics of leaves in different com of leaves in different com of leaves in different com of leaves in different com of leaves in different com of leaves in different com of leaves in different comof leaves in different comof leaves in different com of leaves in different com of leaves in different comof leaves in different com mon plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by plants species growing along the road side of Quetta city were calculated by measuring the measuring the measuring themeasuring themeasuring the foliage length, width, area and petiole length. All these investigated parameters showed showed significant reduction in the polluted sites plant species. The results also exhibited that there was significant variation in the growth of morphological attributes from season to season, specie to specie and site to site (polluted and non-polluted). The effect of air pollution on anatomical characteristics of leaf epidermis revealed that total average number of epidermal cells/mm2 and stomata/mm2 at adaxial and abaxial side shown non-significant variation among polluted and non-polluted sites throughout the year. However there was variation from specie to species and on adaxial & abaxial sides. The number of closed, abnormal/injured and open stomata/mm2, in different investigated plant species were slightly to highly significant (P<0.05 & 0.01) different between polluted and non-polluted sites. Further that highest number of closed and abnormal/injured stomata/mm2 was recorded during autumn from polluted site and maximum number of open stomatas was found during spring from non-polluted site plant species.