Search or add a thesis

Advanced Search (Beta)
Home > Swims: A Sentiment Analysis Approach With Semi-Supervised Feature Weighting and Intelligent Model Selection

Swims: A Sentiment Analysis Approach With Semi-Supervised Feature Weighting and Intelligent Model Selection

Thesis Info

Access Option

External Link

Author

Hassan Khan, Farhan

Program

PhD

Institute

National University of Sciences & Technology

City

Islamabad

Province

Islamabad

Country

Pakistan

Thesis Completing Year

2016

Thesis Completion Status

Completed

Subject

Applied Sciences

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/8116/1/Farhan_Hassan_Khan_Soft_Engineering_HSR_2017_NUST_22.11.2017.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727424022

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Sentiment Analysis is currently one of the most studied research fields. Its aim is to analyze people‟s sentiments, opinions, attitudes etc., towards different elements such as topics, products, individuals, organizations, and services. Sentiment analysis can be achieved by machine learning or lexical based methodologies or a combination of both. Recent research shows that domain specific lexicons perform better as compared to domain independent lexicons. In an effort to improve the performance of domain independent lexicons, this research incorporates machine learning with a lexical based approach, introducing a new approach called SWIMS, to determine the feature weight based on a well-known general-purpose sentiment lexicon, SentiWordNet. Support vector machine is used to learn the feature weights and an intelligent model selection approach is employed in SWIMS in order to enhance the classification performance. The features are selected based on their subjectivity and the effects of feature selection with respect to their part of speech information are studied extensively. Seven benchmark datasets have been used in this research, including large movie review dataset, multi-domain sentiment dataset and Cornell movie review dataset, all of which are freely available online for research purposes. In-depth performance comparison is conducted with the state of the art machine learning approaches, lexical based methodologies, and other tools used for sentiment detection. The proposed SWIMS approach attained accuracy, precision, recall and f-measure values of 83.06%, 83.30%, 82.83% and 83.03% respectively, averaged over the seven datasets. The evaluation of performance measures proves that the proposed approach outperforms other techniques for sentiment analysis.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

آن لائن لیکچر

آن لائن لیکچر

شاہد اشرف

گزشتہ ایک برس کے دوران میں کووڈ کی وجہ سے آن لائن لیکچر دیتے ہوئے وہ کئی تجربات سے گزرا۔ پہلے پہل وہ اپنے دھیان میں لیکچر دیتا رہا۔ کچھ دنوں بعد اسے کیمرہ آف ہونے کے باوجود سٹوڈنٹس کی موجودگی اور عدم موجودگی کا اندازہ ہونے لگا۔ کبھی کبھی وہ کسی طالب علم کی موجودگی کی تصدیق کے لیے سوال بھی پوچھ لیتا تھا اور اس کا اندازہ درست نکلتا تھا۔ آہستہ آہستہ اسے مکمل ادراک ہونے لگا کہ کیمرہ آف ہونے کے باوجود کون سٹوڈنٹ موجود ہے اور کون لنک جوائن کرنے کے بعد سو گیا ہے ۔ ذہنی رابط برقی رابطے سے زیادہ موثر محسوس ہونے لگا۔ وہ کیمرہ آف ہونے کے باوجود دیکھنے پر قادر ہو گیا۔ کسی سٹوڈنٹ کا تصور کرتے ہی اس چہرے پر ہویدا اداسی ، بیزاری ، انہماک، دلچسپی اور نیم دلی سمیت دیگر کیفیات کا انکشاف ہونے لگتا تھا۔ وہ صرف غور سے آئی ڈی کی طرف دیکھتا اور سٹوڈنٹ کی ذہنی کیفیت ظاہر ہو جاتی۔ وہ مخاطب ہوئے بغیر کسی سٹوڈنٹ کی کیفیت پر رائے دیتا اور پھر متعلقہ سٹوڈنٹ کی حیرت کو انجوائے کرتا تھا۔ وہ دوران تدریس بہت سے تجربات سے گزرا ۔ اس کے دل میں ایک خیال زور پکڑنے لگا ۔ اس نے خیال کو جھٹکنے کی کوشش کی مگر ناکام رہا۔ اسی خیال کے زیرِ اثر ایک دن اس نے تمام سٹوڈنٹس کو کیمرے آن کرنے کا کہا ۔ سٹوڈنٹس اپنے اپنے کیمرے آن کر بیٹھ گئے ۔ وہ سب کو دیکھ سکتا تھا مگر اسی لمحے اسے شدید دھچکا لگا ۔ وہ کسی بھی سٹوڈنٹ کی کیفیت کو پڑھنے سے قاصر تھا ۔

 

 

 

جدید علوم کی تدریس اسلامی تعلیمات کے تناظر میں

Education is a compulsory component of life. The first man of this world Adam (A.S) has got his basic education through the angels by the permission and grace of Almighty Allāh. In the light of the Qur’ānic verse “and He taught Adam the names of all the articles (things), the importance of education for the mankind was very well proved. The last and the final Prophet Muhammad (PBUH) was sent by Almighty Allah for the completion of edÉucation as a code forever in the shape of Qur’an and Sunnah but with the passage of time, education has expanded and modern issues and sciences have become the integral parts of today’s educational system. There are many aspects of education especially in the present time, the Western World have explored new angles of discoveries, inventions, and creations through education. How Islam looks into these new issues and matters of education, has been discussed in this article.

Elucidation of Molecular Genetic Basis of Schizophrenia and Primary Microcephaly in Pakistani Population

The high degree of consanguineous marriages, languages, and religion are important factors responsible for high frequency of diverse hereditary disorders in Pakistani population. High incidence of inherited disorders is an ideal substrate to initiate molecular studies in Pakistani population. In this thesis I have systematically identified, phenotyped and sampled complex disorder (Schizophrenia) and rare Mendelian disorder (Primary Microcephaly) in families of different ethnicities/regions in Pakistan. Schizophrenia is a chronic neuropsychiatric disease afflicting around 1.1% of the population worldwide. The symptoms appear in late adolescence or early adulthood, and mainly manifest as hallucination, delusions, cognitive deficit, abnormal moods and behavior. In this thesis 16 multiplex schizophrenia families were systematically identified, diagnosed and sampled from different ethnicities/regions of Pakistan, along with a second cohort of 508 unrelated Pakistani schizophrenia patients. Fifteen out of the sixteen families were excluded for the presence of pathogenic Copy Number Variations (CNVs) by genome wide array screening. While in one of the 16 families pathogenic rare novel duplication was detected on chromosome 5q14.1_q14.2 that truly segregated with the phenotype. Exome sequencing of schizophrenia families revealed three rare and eight common variants in two families. A set of top schizophrenia candidate genes (MIR137, CACNA1C, CSMD1, GRM3 and DRD2) was selected to evaluate their association with schizophrenia in Pakistani population. A case control association study revealed a significant difference in the genotype and allele frequencies of three SNPs between the patients and controls (p = 0.000). Autosomal Recessive Primary Microcephaly (MCPH) is a neurodevelopment defect, characterized by congenital reduction in Occipitofrontal Circumferance (OFC)/Head Circumference (HC) is at least 4 standard deviations (SD) below the ethnically matched, age and sex related mean. MCPH is associated with some degree of mental retardation which persists throughout their life without additional xx morphological or clinical symptoms. The prevalence of primary MCPH is 1 in 10,000 in Pakistani population. In this thesis six consanguineous MCPH families originating from different cities of Punjab were analyzed. Linkage analysis and exome sequencing revealed four novel and two known mutations in MCPH families. The findings in this study will help in understanding the disease mechanism and related pathways as well as annotating various entities of genome. This knowledge will help in efficient carrier screening, genetic counseling and prenatal diagnosis of affected families and ultimately to development of effective therapeutic approaches.