Search or add a thesis

Advanced Search (Beta)
Home > N Enhanced Framework for Sentiment Analysis of Social Media Contents Using Supervised Learning Techniques

N Enhanced Framework for Sentiment Analysis of Social Media Contents Using Supervised Learning Techniques

Thesis Info

Access Option

External Link

Author

Rana Iqrar Ahmad

Institute

Virtual University of Pakistan

Institute Type

Public

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Software Engineering

Language

English

Link

http://vspace.vu.edu.pk/detail.aspx?id=339

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676721027657

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Sentiment analysis or opinion mining is proven to be very effective to analyze huge and complex amount of text of social media. Social media provides an online environment for the users to show their behaviors and emotions through tweets and post. Massive amount of personal information is placed on the World Wide Web due to huge usage of social media. Moods and emotions of the user are different from each other. Sentiment analysis of any written text especially social media content is applicable to extract the opinions, emotions and meaningful insights for better decision making. There are many challenges in the accurate and reliable sentiment analysis of available social media content. The challenges can be both technical and theoretical. Machine learning-based sentiment analysis techniques have issues such as huge lexicon, semantic gap, handling of negation, domain dependency and bi-polar words. Previously, many machine learning and data mining techniques have been proposed by several researchers to resolve these issues. However, the existing techniques have failed to provide satisfactory and reliable results for most of the available datasets. A novel methodology is proposed to overcome above mentioned issues using better and simplified way with less computational complexity and high reliability. Data acquisition, feature encoding, data preprocessing, feature selection, and classification are the various phases of implemented framework. Data gathering and preprocessing step is very critical in the analysis of data. The proposed research mainly contributes during data preprocessing, feature encoding, and classification phases. In feature encoding phase, a hybrid approach of bi-gram and tri-gram is used for word embedding. In the experiments, several benchmark datasets have been utilized to evaluate the effectiveness of the proposed framework. The results obtained from the proposed xii methodology show better or at least comparable results with maximum confidence. The outcome of the proposed work will be helpful to enhance the process of sentiment analysis of social media contents. The experimental results of the framework will be validated using WEKA simulation software.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

ایڈورڈ براؤن

براؤن، ایڈورڈ

            علمی دنیا میں نئے سال کا سب سے افسوس ناک سانحہ مشہور انگریز مستشرق پروفیسر ایڈورڈ جی براؤن کی وفات ہے، موصوف نے اس مہینہ کے آغاز میں غالباً ساٹھ پینسٹھ سال کی تخمینی عمر میں انتقال کیا، وہ پہلے کیمبرج میں فارسی کے لکچرر تھے، پھر ۱۹۰۲؁ء میں وہ عربی کے پروفیسر مقرر ہوئے، انھوں نے طب کی تعلیم بھی حاصل کی تھی، عربی میں وہ پروفیسر پامر کے شاگرد تھے، ان کی سب سے جامع، مسبوط اور مشہور تصنیف لٹریری ہسٹری آف پرشیا کی ضخیم جلدیں ہیں، موصوف نہ صرف علمی حیثیت سے بلکہ ایک بے تعصب عالم، ایک ہمدرد مشرق اور ایک شریف انسان ہونے کے لحاظ سے بھی نہایت بلند درجہ تھے، قومی تنگ ظرفی اور مذہبی عصبیت سے وہ قطعاً مبرا تھے، ان آنکھوں کو یہ عزت حاصل ہے کہ انھوں نے مرنے والے کی زیارت کی تھی، آئندہ معارف میں ان کے کچھ حالات سپرد قلم ہوں گے، ہندوستان میں ان کو ہم سے بہتر جاننے والے اشخاص بلکہ ان کے شاگرد موجود ہیں، کیا بہتر ہو اگر ان میں سے کوئی صاحب ہماری مدد فرمائیں اور براؤن پر ایک عمدہ مضمون لکھ کر عنایت فرمائیں اور اگر احباب پسند کریں تو معارف کا ایک نمبر صرف براؤن پر شائع کیا جائے کہ ان کے احسانات کا یہ ادنیٰ ترین معاوضہ ہے۔  (سید سليمان ندوی، جنوری ۱۹۲۶ء)

Optimizing Sensory Loads Using a Sensory Processing Skills Therapy among Autistic Spectrum Disorder

IntroductionSensory integration therapy can improve language skills, attention, and social interactions in children with ASD. However, it is also important to note that research in this field is ongoing, and more studies are needed to confirm the effectiveness of these therapies. The present study is aimed to identify the effects of occupational therapy-based sensory processing skill therapies in improving the autism severity and QoL among ASD children. MethodologyThe intervention was performed for 12 weeks, six sessions per week, each based on 60 minutes of duration. The treatment protocol comprised four sensory processing skills in which Each child was trained on every skill for 15 minutes, making a total of 60 minutes of duration for a single session. ResultsSignificant improvements in CARS, CGAS and PedsQL (p<0.001) were observed after 12-weeks of intervention. ConclusionSensory processing skills therapies are a practical treatment approach in optimizing sensory load among ASD children.   DOI: https: //doi. Org/10.59564/amrj/01.01/005

Indentification of Genes Responsible for Intellectual Disability in Consanguineous Families

Intellectual disability (ID) or cognitive impairment is clinically and genetically a heterogeneous disorder. The extreme genetic heterogeneity is evident from the identification of approximately 2500 ID genes (also include autosomal recessive ID genes) but despite this recent progress underlying genes are still unknown in the large number of ID patients/families. Here we present 8 consanguineous Pakistani families which have multiple individuals with autosomal recessive ID. Affected members of these families mainly presented ID, but detailed clinical evaluations also showed the presence of additional features in some ID patients including facial dysmorphism, microcephaly, polydactyly, hypopigmented skin, strabismus, hypotonia, cerebellar ataxia, myotonic dystrophy, cerebral palsy and micrognathia. DNA samples collected from all available members of these eight families were used for whole genome genotyping and homozygosity mapping was performed to identify the homozygosity by descent (HBD) regions. Homozygosity mapping led to the identification of single HBD region in family G, but all other families have multiple HBD regions. Majority of the detected HBD regions do not overlap with each other and thus ruled out the involvement of the same gene in these families. Subsequently, DNA samples from one patient from each family was used for exome sequencing to identify the ID causing variant. However, the analysis and filtering of variants obtained by exome sequencing identified 28 potentially pathogenic variants, which were tested for segregation in the respective families. Further analysis of these 28 variants and segregation tests helped to reduce the list of 28 variant to nine potential variants. The potential variants were identified in TRAPPC10 (Family A), RAB11FIP1 (Family B), CWF19L1 (Family C), WDR19 (Family D), SYNE1 (Family E), ALG3 (Family F), AP4M1 (Family G), DUOX2 (Family H) and ZNF54 (Family H) genes. Among the identified variants, variants in novel candidate genes were identified in family A and family B, but other variants were identified either in the known ID gene or in gene involved in ID spectrum disorders. In family A, a variant (c.C2786T; p.P929L) in TRAPPC10 was detected in the proband, which segregate with the ID phenotype in this family. This variant affects the C terminal region of TRAPPC10, and is predicted to affect its interaction with TRAPPC9 protein. Similarly, in family B a missense variant (c.451A>C; pAsn151His) in exon 2 was identified which is predicted to affects the C2 domain of the protein at N terminus end and probably decreases the GTP binding efficiency of this domain. Microscopic analysis of hair samples of proband from this family showed the irregular pattern of melanin indicating the improper transportation of proteins. The genes identified in both the families play role in the vesicle transport and it is anticipated that loss of function variant identified in family A and B probably compromise this role and thus may cause ID in the affected individuals of both families. In family C, a nonsense variant (c.C949T; p.Q317X ) was identified in CWF19L1 gene, whereas affected members of family D carry a missense variant (c. 3521G>A; p.R1174H) in WDR19 gene. Both these variants are novel but CWF19L1 and WDR19 genes are already known to cause ID. However, affected members of families E, F and G have pathogenic variants in SYNE1 (p.R82L), ALG3 (c.274G>T; p.Ser270Leu) and AP4M1 (c.193-194delTA; p.Y65FfsX50) genes, respectively and these genes are known to cause disorders which also include ID. The variants identified in these families are novel except the variant in AP4M1 gene which has been already reported in a Pakistani family. In family H, exome sequence analysis identifies two potential variants in DUOX2 and ZNF541 genes, but we could not establish the pathogenic nature of these potential variants with certainty. Though the variants in DUOX2 gene has recently been associated with ID in patients with congenital hypothyroidism but testing of thyroid function of two affected members of our family ruled out the thyroid abnormalities in these patients. After ruling out the involvement of DUOX2 variant in this family we looked for additional variants which resulted in the identification of a variant (p. K733N) in ZNF541 gene. However, based on the currently available data it is difficult to ascertain the functional effects of this variant and thus it can be considered as variant of unknown significance (VUS). This study results in the identification of two (TRAPPC10 and RAB11FIP1) ID genes and six reported genes that are associated with ID. The network analysis of the genes identified in this study showed the involvement of pathways involved in the modification of lipids and proteins, membrane trafficking, maintenance of nuclear integrity and flagellar movements. Together these processes are required for the proper development and functioning of the brain which is needed for higher level functioning such as cognition and the disturbances in these processes can result in ID or related disorder in humans.The work presented in this thesis results in the following publications: 1. Ricardo Harripaul, Nasim Vasli, Anna Mikhailov, Muhammad Arshad Rafiq, Kirti Mittal, Christian, Muhammad Ilyas, Falak Sher Khan, Valeed Khan, Mohammad Moradi, Muhammad Ayaz, Farooq Naeem, Abolfazl Heidari, Peter John, Iltaf Ahmed, Zehra Agha, Asif Mir, Muhammad Ansar, Leon French, Muhammad Ayub, John B. Vincent. Mapping autosomal recessive intellectual disability: Combined microarray and exome sequencing identifies 26 novel candidate genes in 192 consanguineous families. Molecular Psychiatry. 2017 Apr 11. doi: 10.1038/mp.2017.60. 2. Regie Lyn P Santos-Cortez*, Valeed Khan*, Falak Sher Khan, Zaib-un-Nisa Mughal, Imen Chakchouk, Kwanghyuk Lee, Memoona Rasheed, Ehsan Ullah, Muhammad Arif Nadeem Saqib, Izoduwa Abbe, Ghazanfar Ali, Saadullah Khan, Zahid Azeem, Irfan Ullah, Deborah, Wasim Ahmad, Muhammad Ansar, Suzanne M. Leal. Novel candidate genes and variants underlying autosomal recessive neurodevelopmental disorders with intellectual disability. Human Genetics 2018. DOI:10.1007/s00439-018-1928-6.