Search or add a thesis

Advanced Search (Beta)
Home > Authorship Attribution for Urdu Newspapers Columns Using Text Mining Techniques

Authorship Attribution for Urdu Newspapers Columns Using Text Mining Techniques

Thesis Info

Access Option

External Link

Author

Waheed Anwar

Program

PhD

Institute

COMSATS University Islamabad

City

Islamabad

Province

Islamabad.

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/12355/1/Waheed%20Anwar%20Computer%20Sci%202019%20iub%20prr.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727707210

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


With emergence of big data analytics in last decade, the importance of analyzing semistructured and unstructured data (such as text) is also highlighted. Since, the text (such as customer reviews, newspaper articles, etc.) contain significant business information, the text analytics becomes more significant to predict, infer or analyse information to add value to the business. In this research, we present a unified approach for intelligent association analysis of text that how much a piece of text is related to a customer or a person In this dissertation, an approach is presented for Authorship attribution in Urdu text using LDA model with n-grams texts of authors and improved sqrt-cosine similarity for the sake of forensic analysis. The proposed approach uses n-grams words to identify various learned representations of stylometric features and use them to identify the writing style of a particular author. The LDA based approach emphasizes instance-based and profile-based classification of an author’s text. Here, LDA suitably handles high dimensional and sparse data by allowing more expressive representation of text. The presented approach is an unsupervised computational methodology that can handle the heterogeneity of the dataset, diversity in writing styles of authors, and the inherent ambiguity of the Urdu language. A large corpus has been collected for performance testing of the presented approach. The results of experiments show superiority of the proposed approach over the state-of-the-art representations and other algorithms used for Authorship attribution. Manifold contributions of the presented work are use of improved sqrt-cosine similarity with LDA topics to measure similarity in vectors of text documents for the forensic analysis purpose, construction of a large data set of 6000 documents of columns, and achievement of 92% results on Urdu columns with fifteen authors and 78.57% results on PAN12 English dataset with fourteen authors without using any labels for authorship attribution task.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

مولوی مظہر الحق

مولوی مظہرالحق صاحب پٹنہ
جس طرح ہمارا پرانا سال ایک بڑے قومی حادثہ یعنی پرانی تعلیم کے ایک بہترین نمونہ (مولانا حبیب الرحمان عثمانی دیوبندی) کے دائمی فقدان پر ختم ہوا، اسی طرح ہمارے نئے سال کا آغاز بھی ایک بڑے قومی حادثہ یعنی نئی تعلیم کے ایک بہترین نمونہ (مولوی مظہرالحق صاحب بیرسٹر پٹنہ) کی دائمی جدائی سے ہوا، مولوی مظہرالحق صاحب مرحوم کی قومی و سیاسی حیثیت تو الگ ہے، ان کی اخلاقی اور علمی حیثیت بھی کچھ کم قابل ذکر نہیں ہے، وہ فارسی سے واقف، عربی سے آشنا، انگریزی کے ادیب و خطیب اور فلسفہ کے نہایت دقیقہ رس طالبعلم تھے، ان کے علمی کارناموں کا آغاز طوفان نوح کی بحث سے ہوا، الپنچ پٹنہ اور وقت گورکھپور ان کے ابتدائی علمی مباحث کے جولان گاہ تھے، ان کی سب سے آخری علمی تحریر غالباً وہ ہے جو ابھی ابھی پونہ سے شائع ہونے والی انگریزی کی کتاب تصوف و روحانیت پر مقدمہ ہے، وہ نسباً فاروقی تھے، اس لئے ان کی اخلاقی قوت و جرأت کیا سلطنت اور کیا قوم دونوں کے مقابلہ میں برابر تھی، وہ جس کو حق سمجھتے تھے اس کے اظہار میں نہ ان کو سلطنت کی پروا ہوتی تھی اور نہ قوم کی، ان کا یوروپین طرز معاشرت کو الوداع کہہ کر وفعتہ مشرقی اور غالی مشرقی بن جانا ان کی بے مثال اخلاقی جرأت کا نمونہ ہے، مرحوم کی آخری عمر روح و روحانیت کی تحقیق میں صرف ہوئی، خدا ان کی روح کو اپنی مغفرت کی لازوال دولت سے مالا مال کرے، اب وہ وہاں پہنچ چکی ہے، جہاں کے کشف زار کے لئے وہ بے قرار تھی۔ (سید سلیمان ندوی، جنوری ۱۹۳۰ء)

 

Return Migration to Pakistan during COVID19 Pandemic: Unmaking the Challenges

In order to contain the spread of corona virus (COVID-19) disease, strict border closure measures have been taken globally. Migrants and refugees are affected across the globe due to such measures. Amid the COVID-19 pandemic, the economic recession escalated across the globe which is expected to have serious implications for the migrant workers and laborers. Potohar region was selected to explore implications of return migration from abroad, but the fieldwork halted immediately due to the pandemic outbreak. Since the data on Pakistani migrants is dispersed and scant, it was nearly impossible to stick to the locale for returnees. Therefore, the data for this study was collected qualitatively using exploratory methodology. In-depth interviews were conducted using interview guide as a tool of research. The paper is based on analysis of the narratives based on the experiences of the returnees especially. It sheds light on the state of the stranded Pakistani migrants who have been returning or awaiting repatriation due to layoffs. It delves into long-run and short-run challenges due to return migration, in Pakistan which highly depends on remittances from abroad. Challenges created by sudden end to remittances, entrepreneurial setups and returnees’ reintegration in the society need immediate attention. It is recommended that the state should support and monitor the migrants living abroad, ease out issues in repatriation of the laid off workers, pave way for investment, offer insurance plans, reduce reliance on remittance flow and engage them in Public Private Partnerships for sustainable reintegration.

Evaluation of Different Stress Indicators Associated With Repproductive Cyclicity of Crossbred Dairy Cows

Eminent environmental temperature has adverse affect on dairy cattle production and reproduction. The periparturient period is also very critical for reproductive functions of dairy cows. A variety of methods are used to improve fertility in these stress conditions. The present study was conducted under a series of three experiments to find out stress-reproduction relationship and effect of vitamin E on this interaction. Study-I, was conducted to assess physiological and reproductive changes, in relation to heat stress in different dairy cattle breeds in various seasons. A total of thirty six lactating dairy cows, nine from each breed of local (Sahiwal and Achai), Cross-bred (Sahiwal x HF) and Holstein Friesian were selected. Sampling was conducted when the cows were in the di-estrus phase of the estrus cycle in February (thermoneutral), April (thermotransitional) and June (thermal stress) at an average environmental temperature of 18°C, 32°C and 42°C respectively. A significant decrease in Daily milk yield (DMY) was observed in all breeds with increase in environmental temperature (P < 0.01). DMY also varied significantly (P < 0.001) among breeds. The HF dairy cows showed the highest mean DMY followed by cross-bred, Sahiwal and Achai at all the three seasons. BCS was not affected by environmental temperature; however, BCS varied among breeds significantly (P < 0.01). A significant increase in all the physiological parameters (rectal temperature, respiratory rate and pulse rate) was observed in all dairy cows with increase in environmental temperature during thermo transitional and summer seasons in April and June respectively. Thermal stress in June increased concentrations of glucose (P= 0.014), cortisol (P < 0.001), heat shock protein-70 (HSP-70) (P < 0.001) and follicular numbers (P < 0.01), while decreased progesterone concentrations (P < 0.01) in all four breeds as compared to February. DMY and progesterone level are negatively correlated with environmental temperature. Glucose and cortisol levels were positively correlated with each other and negative with Progesterone. Positive correlation was found between glucose, cortisol and HSP-70 with rise in environmental temperature. However progesterone was negatively correlated with these parameters at high environmental temperature. It is concluded that the intensity of changes was higher in HF and cross-bred dairy cows than local Achai and Sahiwal, suggesting that extra managemental and therapeutical support is needed to improve fertility of these breeds in tropical regions. Study-II, was designed to detect the occurrence of oxidative stress in dairy cows by determining the plasma malondialdehyde (MDA) concentration during the periparturient period and its possible relationship with dairy cows fertility. Thirty-six periparturient lactating dairy cows, nine from each breed of Sahiwal, Achai, Cross-bred (Sahiwal x HF) and Holstein Frisian were selected. Sampling was conducted on post partum day (P.P.Day) 60, 82 and 105 of the lactation stage during the diestrus period of the estrus cycle. DMY varied significantly with P.P Days and among breed (P < 0.001). Highest DMY was shown by HF followed by cross-bred, Sahiwal and lowest by Achai. The interaction (PP.Days x Breed) effect was also highly significant (P < 0.01) for DMY. Serum glucose concentration significantly increased with increase in PP.Days (P < 0.01). Breed also affected glucose concentration (P < 0.001). A decrease in MDA concentrations were observed with increase in PP.Days (P < 0.001) from P.P day-60 to 82 and 105. Breed also affected the MDA concentrations significantly (P < 0.001), more prominent in HF and cross-bred. Both P.P. Days and breed significantly affected the serum cortisol concentration (P < 0.001). The cortisol concentration significantly decreased from P.P day-60 to 82 and 105. Progesterone level increased in all breeds (P < 0.05) with increase in P.P. Days (P < 0.001) from day-60 to 82, continued up to day-105. BCS was negatively correlated with serum cortisol, glucose and progesterone. Cortisol, DMY and MDA were positively correlated with each other and negative with progesterone and P.P. Days. The study revealed that HF and cross-bred dairy cows were more prone to oxidative stress than local breeds. Correlations analysis indicates that high milk production delayed ovarian activity effecting the reproduction of periparturient cows as assessed by progesterone concentrations. Therefore, it is suggested that higher genetic merit milk breeds should give extra managemental support for their better productivity and fertility. Study-III, was designed to find out the response of different breeds to vitamin E supplementation in combating stress and improving reproductive cyclicity. The experiment was conducted on thirty six lactating dairy cows, nine from each breed of Sahiwal, Achai, Cross-bred (Sahiwal x HF) and Holstein Frisian. Vitamin E was supplemented to all dairy cows in feed at a dose rate of 1000 IU/ cow/ day. Sampling was conducted on day-zero (control) before Vitamin E supplementation, day-20 and day-40 of Vitamin E supplementation during the diestrus phase of the estrus cycle. Daily milk yield and BCS varied significantly among breeds (P < 0.001) with no significant effect of vitamin E. Serum glucose increased significantly (P < 0.05) with vitamin E supplementation, but did not varied among breeds significantly. There was significant increase in SOD and GPx with vitamin E supplementation (P < 0.001). Breeds also varied in super oxide dismutase (SOD) and glutathione per oxidase (GPx) activities (P < 0.05, P < 0.001 respectively) with more increase in GPx in local dairy breeds. Stress markers, plasma MDA and HSP-70 and serum cortisol concentrations decreased significantly (P < 0.001) with vitamin E supplementation with significant variations among breeds (P < 0.001). Progesterone concentration increased significantly (P < 0.001) in all breeds with vitamin E. Breed effect on progesterone concentrations was also found significant (P < 0.05). Local breeds showed higher progesterone concentration while overall increase was found higher in Cross-bred dairy cows (39.95%). Number of dominant follicles decreased significantly with vitamin E supplementation (P < 0.01) in all the dairy breeds, highest in cross-bred dairy breeds. Breed also showed significant effect on number of follicles (P < 0.05). DMY showed positive correlation with MDA and negative with SOD, GPx and progesterone. The stress markers (cortisol, HSP-70 and MDA) were positively correlated with each other and glucose concentration while negative with antioxidant markers. Antioxidant markers were positively correlated with progesterone. It can be concluded that improved milk breeds showed more prominent response to vitamin E supplementation than local breeds suggesting regular feeding of antioxidant to these breeds for better performance.