Search or add a thesis

Advanced Search (Beta)
Home > Redefining Urdu Morphology and Grammar for the Development of an Integrated Sentiment Analysis Framework

Redefining Urdu Morphology and Grammar for the Development of an Integrated Sentiment Analysis Framework

Thesis Info

Access Option

External Link

Author

Syed, Afraz Zahra

Program

PhD

Institute

University of Engineering and Technology

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2013

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/2223/1/2773S.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727820602

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


The rise of social networking sites and blogs has simulated a bull market in personal opinion; consumer recommendations, product reviews, ratings, and other types of online expressions. For computational linguistic researchers, this fast-growing heap of information has opened an exciting research frontier, referred as, the Sentiment Analysis (SA). For English, this area is under consideration from last decade. But, other major languages, like Urdu, are totally overlooked by the research community. Urdu is a morphologically rich and recourse poor language. The distinctive features, like, complex morphology, flexible grammar rules, context sensitive orthography and free word order, make the Urdu language processing a challenging problem domain. For the same reasons, sentiment analysis approaches and techniques developed for other well-explored languages are not workable for Urdu text. This dissertation presents a grammatically motivated, sentiment classification framework to handle these distinctive features of the Urdu language. The main research contributions are; to highlight the linguistic (orthography, grammar and morphology, etc.) as well as technical (parsing algorithm, lexicon, corpus, etc.) aspects of this multidimensional research problem, to explore Urdu morphological operations, grammar and orthographic rules, to redefine these operations and rules with respect to the requirements of sentiment analysis framework. The orthographical, morphological, grammatical and finally the conceptual details of the language are our target concerns. Additionally, our approach can help in the sentiment analysis of other languages, like Arabic, Persian, Hindi, Punjabi etc. The proposed framework emphasizes on the identification of the SentiUnits, rather than, the subjective words in the given text. SentiUnits are the sentiment carrier expressions, which reveal the inherent sentiments of the sentence for a specific target. The targets are the noun phrases for which an opinion is made. The system extracts SentiUnits and the target expressions through the shallow parsing based chunking. The dependency parsing algorithm creates associations between these extracted expressions. The framework uses the sentiment-annotated lexicon based approach. Each entry of the lexicon is marked with its orientation (positive or negative) and the intensity (force of orientation) score. The experimentation based evaluation of the system with a sentiment-annotated lexicon of Urdu words and two corpuses of reviews as test-beds, shows encouraging achievement in terms of accuracy, precision, recall and f-measure.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

خلاصہ بحث

آخرت پر ایمان لانے کا مطلب یہ ہے کہ وفات کے بعد سے لے کر جنت یا جہنم میں داخل ہونے کے بارے میں قرآن اور حدیث میں میں تمام احکامات کی تصدیق کرنا اور اس پر یقین رکھنا کیونکہ کہ عقیدہ آخرت شرط ارکان ایمان کا اہم جز ہے اور اس پر ایمان لائے بغیر مکمل مومن نہیں ہو سکتے، اس لیے اسلام میں عقیدہ آخرت کی بہت اہمیت ہے ۔ اس فصل میں تفسیر تفہیم القرآن قرآن کی روشنی میں آیت استفہام اور عقیدہ آخرت کی وضاحت کی گئی ہے جو کہ درج ذیل آیات ہیں:

 سورۃ الرعد آیت نمبر ۵، سورۃ العنکبوت آیت نمبر۱۹،۲۰، سورۃ الروم آیت نمبر ۸۹، سورۃ السجدہ آیت نمبر ۲۲،۲۶،۲۸،، سورہ فاطر آیت نمبر ۳۷، سورۃ الزمر آیت نمبر ۱۹، سورۃ ق آیت نمبر ۱۵، سورۃ الطور آیت نمبر۱۵ ،سورۃ القیامہ آیت نمبر۳ ، سورۃ النازعات آیت نمبر ۲۷ ،سورۃ الغاشیہ آیت نمبر ۱۔

Vivekananda’s Views on Christianity and Islam

Vivekananda was the Hindu revivalist of nineteenth century who preached the message of equality of all religions. In his lectures, he guided people to assimilation of religions and not their destruction. He emphasized on peace and harmony of religions that could only be attained through tolerance. This paper explores his claim of equality of religions from his writings regarding two religions - Christianity and Islam. Critical approach is utilized to identify the fact that either he is equating all religions or he is trying to submerge the non-Hindu religions in his philosophy of neo-Vedanta. Apparently, the tension between these two positions makes his theory of pluralism suspicious. In other words, his popular image of being a pioneer of religious pluralism needs to be reassesses by studying his writings and presentation of the beliefs, rituals, and practices of other religions, as well as, his practical interactions with the followers of different religions during his life. In this connection, it is important to explore how he perceives and depicts the personalities of Jesus Christ and Muhammad.

Taxonomic, Phytochemical and Biological Screening of Some Selected Medicinal Plants of Lesser Himalaya Pakistan

Medicinal use of plants is as old as the history of mankind. Medicinal plants have the ability to produce valuable classes of compounds with interesting bioactivities. Due to increasing side effects of synthetic drugs, use of medicinal plants is increasing day by day. Pakistan has about 6000 species of higher plants, of which about 700 species are commonly used for medicinal purposes. Taxonomic, Phytochemical and Biological Screening of Some Selected Medicinal Plants of Lesser Himalaya Pakistan was carried out to determine the accurate taxonomic description, complete phytochemical profile and bioactivity of selected medicinal plants. Four medicinal plants, Spermadictyon suaveolens, Reinwardtia indica, Xylosma longifolium and Celtis eriocarpa were selected based upon ethnomedicinal importance and their least phytochemical exploration. Selected plants were analyzed for taxonomic evaluation, qualitative and quantitative phytochemical screening, proximate analysis, biological activities and LC-MS profiling. R. indica was also analyzed for isolation of phytochemicals. Selected plants were extracted with cold maceration and fractionated in n-Hexane fraction (HF), chloroform fraction (CF), ethyl acetate fraction (EF) and aqueous fraction (AF). Preliminary phytochemical tests revealed the presence of high amount of phenolics and flavonoids in all four plants. R. indica contains high amount of phenolic, flavonoid, tannin, terpenoids and low amounts of alkaloids and saponins. C. eriocarpa contains high amount of phenolic, flavonoid, tannin and terpenoids, while low amount of saponins. S. suaveolens contains high amount of phenolics, flavonoids and tannins. X. 1 2 longifolium contains high amount of phenolics, flavonoids, alkaloids and tannins, while low amount of terpenoids and saponins. Proximate analysis revealed that X. longifolium contains high amount of dry matter (90.30±0.14), low moisture content (9.70±0.14), high fiber, carbohydrates and nutritive values (353.66±0.70). R. indica and X. longifolium showed higher total phenolic contents. High total flavonoid content was found in crude methanolic extract (65.90±1.00) and ethyl acetate fraction (88.01±1.33) of R. indica. Total flavonoid content is also higher in chloroform (74.81±1.58) and ethyl acetate fraction (79.84±0.80) of X. longifolium. R. indica showed higher antioxidant, cytotoxic and antitumor activities in crude methanolic extract, chloroform and ethyl acetate fractions. The highest DPPH EC50 value was exhibited by ethyl acetate fraction (119.64±0.58) followed by crude methanolic extract (209.00±1.53). Chloroform fraction of R. indica also showed higher antitumor IC50 (255.90±0.97), followed by ethyl acetate fraction (297.663±0.91). C. eriocarpa showed higher antioxidant (324.81±2.60), cytotoxic (243.61±1.24) and antitumor (372.76.±0.34) activities only in ethyl acetate fraction. S. suaveolens revealed higher antioxidant activity in ethyl acetate fraction (149.15±0.59) followed by Chloroform fraction (208.13±1.78). X. longifolium showed higher antioxidant activity in crude methanolic extract (107.21±0.16) followed by ethyl acetate fraction (152.96±0.43) and chloroform fraction (187.95±0.26). X. longifolium also showed high cytotoxic and antitumor activity in EF (484.19±1.55 and 235.41±1.51 respectively). UHPLC-DAD-ESI-MS profiling yielded identification of 58 compounds in R. indica, 48 compounds in C. eriocarpa, 50 compounds in S. suaveolens and 60 compounds in X. longifolium. LC-MS profile and bioactivity revealed that bioactivity 3 of R. indica extracts is mainly due to phenolic acids and flavones derivates, C. eriocarpa is due to flavones derivatives, S. suaveolens is due to phenolic acids, Quercetin and luteolin derivatives, while X. longifolium is due to Quercetin, naringenin and apigenin derivatives. UHPLC-MS profile also revealed that S. suaveolens and X. longifolium are rich in Quercetin derivatives. Based upon promising results of bioactivities of R. indica it was selected for compound isolation. Two compounds, Diferuloyl sinapic acid and Esculin were isolated for the first time from R. indica. The present research was very helpful in determining the underlying phytochemical profile and bioactivity correlation of selected medicinal plants.