Search or add a thesis

Advanced Search (Beta)
Home > Location Based Sentiment Mapping of Topics Detected in Social Media

Location Based Sentiment Mapping of Topics Detected in Social Media

Thesis Info

Access Option

External Link

Author

Muhammad Abbas

Institute

Virtual University of Pakistan

Institute Type

Public

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2018

Thesis Completion Status

Completed

Subject

Software Engineering

Language

English

Link

http://vspace.vu.edu.pk/detail.aspx?id=199

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676720992770

Similar


Social media has risen as a powerful social link among people. It gives them an easy, unsupervised, rapid and flexible platform for sharing information with each other. It serves like a virtual environment where there is no direct or indirect executive power to dictate their opinions. They feel free to appreciate or criticize the actions of others. That is why social media posts carry true reflection of public feelings over any social event. This very nature of social media content makes it a valuable asset for research community to dig deeper and find meaningful concerns out of its huge chunks. This research work explores how people across different regions of Pakistan think about any social media topic. The research work proposed a model to extract spatial, topical and sentimental information of social media posts and combine them together to perform location-based sentiment mapping of the topics detected in social media. The study area has been restricted to Pakistan.The research work started with collection of tweets using streaming API of the Twitter. The information contained in a 3rd party dataset worldCities was used to filter out Pakistani tweets and perform indirect conversion of user profile location into geo-location, as geo-location was directly not available with tweets. Probabilistic topic model; Latent Dirichlet Allocation (LDA) was used to extract latent topics from the dataset. CRAN library was used for sentiment classification of the tweets into 3 classes: positive, negative and neutral. The processed dataset was uploaded to a persistent storage Google Drive and then imported into a web based interactive self-written Shiny Application to read geo-spatial, topical and sentimental information of the tweets from processed dataset and produce interactive geographical map. The interactive geographical map has also been supported by heatmap, scatter plots, bar graphs and pie charts in order to enhance visualization process. The novelty of this research work is its location-based visualization of the strength of public opinion on any emerging event or topic in Pakistan.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

بھٹو شہید پارک

بھٹو شہید پارک

جناح پارک راولپنڈی کا نام بھٹو شہید پارک رکھا جائے ۔بھٹو شہید پارک جی ہاں جس کانام اس بدبخت نے جناح پارک میں تبدیل کر دیا تھا ۔اڈیالہ جیل بنانے کا مقصد ہی یہی تھا کہ انہیں اندازہ تھا کہ اگر پاکستان پیپلز پارٹی کی حکومت آتی ہے تو وہ لازمی اس جگہ پر یاد گار بنائیں گے ۔ جہاں چیئر مین بھٹو شہید کو پھانسی دی گئی ۔پنجاب حکومت نے سب سے پہلے تو یہاں پرانی جیل گرا کر ہائوسنگ سکیم کا اعلان کیا یہ راولپنڈی کا مہنگا ترین علاقہ تھا ۔پلاٹ بنا کر نیلام کیے گئے ۔پھانسی گھاٹ والی جگہ بھی پاکستان پیپلز پارٹی کی رہنما آمنہ پراچہ نے سب سے زیادہ قیمت دے کر خرید لی تھی ۔پی پی پی کی حکومت آئی تو وہاں ہائو سنگ سکیم ختم کر کے بھٹو شہید پارک بنا دیا گیا۔وہاں ایک کوٹھڑی بھی تعمیر کی گئی تھی مجھے نہیں معلوم وہ موجود ہے یا ختم کر دی گئی ہے ۔پاکستان پیپلز پارٹی حکومت کا تختہ الٹنے کے بعد نواز شریف پارک تو نہ ختم کر سکا مگر نام تبدیل کر گیا۔میں نے اس وقت اخباری بیانات کے ذریعے باقاعدہ مہم چلائی تھی ۔پھر میں ہانگ کانگ کینیڈا چلا آ یا ۔آج جب یہ وڈیو دیکھی تو زخم تازہ ہو گئے کہ نواز شریف نے بھٹو شہید پارک کا نام تبدیل کیا تھا ۔ویسے یہ تقریر سنو تو کتنی رعونت تھی اس کے لہجے میں۔محترمہ بے نظیر بھٹو شہید اور آصف علی زرداری کے دل کتنے بڑے تھے کہ اس کے باوجود اس سے میثاق جمہوریت کیا بات اور طرف نکل جائے گی ۔کارکنان سے گزارش ہے کہ وہ بھٹو شہید پارک نام واپس کر نے کی فی الحال کم از کم سوشل میڈیا پر مہم چلائیں ۔ کیونکہ یہ پھانسی گھاٹ...

An Empirical Analysis of Male Labour Force Participation in District Lahore

The present study examines the determinants of male labour force participation in district Lahore, Pakistan. The authors have collected data from age cohort 18-64 years by primary source. The results are tested by using logit model. The results show that age, increasing educational levels, parents’ level of education, presence of assets and marital status contribute significantly to higher male participation rate in the workforce.

Sustainable Management of Chilo Partellus Swinhoe and Oligonychus Pratensis Banks on Spring Maize Crop, in Punjab, Pakistan.

Studies were conducted on sustainable management of Chilo partellus (Swinhoe) and Oligonychus pratensis (Banks) on spring maize crop during 2004 to 2006 in the farmer’s field and Acarological Laboratory, Department of Agri. Entomology, University of Agriculture Faisalabad. This dissertation is comprised of following four sections. I. Host Plant Resistance against C. partellus and O. pratensis. II. Role of Weather in Population Fluctuation of C. partellus and O. pratensis III. Physico-morphic and Chemical Plant Characters Responsible for Resistance against C. partellus and O. pratensis. IV. Sustainable Pest Management Approach for the Control of Maize Stem Borer and Mites. I. Host Plant Resistance against C. partellus and O. pratensis Significant variations were found to exist among genotypes regarding plant infestation caused by C. partellus. From the twenty genotypes of maize, viz., Sahiwal- 2002, 34-N-43, Golden, EV-1097, Agati-2002, P-3335, Hicorn 11, C-78, DTC, EV-6098, 32-F-10, FHY-421, Pak Afgoyee, EV-5098, DK-6142, C-20, FHY-845, NK-8441, 32-W- 86 and DK-6525, two genotypes (Sahiwal-2002 and 34-N-43) showing susceptible response, two ( EV-6098 and 32-F-10) showing intermediate trend and two (32-W-86 and DK-6525) showing comparative resistance against C. partellus were selected for final screening. In a final screening trial during 2005, SWL-2002 was found to be the most susceptible genotype that resulted in 13.71 % plant infestation caused by C. partellus whereas the genotype DK-6525 showed a comparatively resistant response with 7.31 % plant infestation. The fourth week of April during 2004 and 2005 was the most favourable period for the development of C. partellus when the maximum plant infestation, i.e., 12.66 % and 23.51 % during 2004 and 2005, respectively occurred. The number of larvae per five plants, tunnel length, height of infested and healthy plants, and 100-grain weight in healthy and infested plants showed significant variations among selected genotypes of maize regarding C. partellus. Maximum reduction in 100-grain weight and height of plants was observed in genotype SWL-2002. Height of infested and healthy plants showed significant and negative correlation with larvae population of C. partellus whereas tunnel length was positively and significantly correlated with the larval population. Weight of 100-grains in infested and healthy plants, and number of tunnels showed non significant correlation with the larval population. Significant variations were found to exist among genotypes regarding leaf infestation caused by O. pratensis. Amongst the above mentioned genotypes, two (Agati- 2002, FHY-421) showing susceptible response, two (DTC, NK-8441) with intermediate response and two (C-20, Pak Afgoyee) showing a resistant trend against O. pratensis were selected for final screening trial during 2005. Agati-2002 was found to be the most susceptible with 14.72 % leaf infestation, whereas Pak Afgoyee was comparatively resistant with minimum leaf infestation i.e. 1.94 % caused by O. pratensis. The second week of June during 2004 and the third week of June during 2005 showed maximum leaf infestation, i.e. 14.58 and 18.89 %, respectively caused by O. pratensis. Role of Weather in Population Fluctuation of C. partellus and O. pratensis The study was conducted to determine the role of weather factors on infestation caused by C. partellus and O. pratensis during 2004 and 2005. The data were processed for simple correlation and multiple linear regression analyses. The results showed that the maximum plant infestation caused by C. partellus during 2004 was recorded to be 12.66 % at 36.47oC maximum temperature, 21.29oC minimum temperature, 28.88oC average temperature, 36.86% relative humidity (RH) and 1.60 mm rainfall on April 25, while during 2005 the maximum plant infestation was observed to be 23.51% at 37.81oC maximum temperature, 17.57oC minimum temperature, 27.69oC average temperature and 28.79 % RH on April 22. The maximum leaf infestation caused by O. pratensis during 2004 was observed to be 14.58 % at 38.16oC maximum temperature, 25.41oC minimum temperature, 31.79oC average temperature, 47.00 % RH and 10.10 mm rainfall on June 13, while during 2005 the maximum leaf infestation was recorded to be 18.89 % at 40.54oC maximum temperature, 24.93 oC minimum temperature, 32.74 oC average temperature, 36.00% RH and 0.00mm rainfall on June 17. Minimum temperature during 2004, maximum temperature during 2005 and average temperature on a cumulative basis showed 57.9%, 68.6% and 25.5% contribution respectively in leaf infestation fluctuation caused by O. pratensis. Physico-morphic and Chemical Plant Characters Responsible for Resistance against C. partellus and O.pratensis. The study was conducted on six genotypes of maize viz. DK-6525, 32-W-86, EV- 6098, 32-F-10, 34-N-43 and Sahiwal-2002 for C. partellus and Pak-Afgoyee, C-20, NK- 8441, DTC, FHY-421 and Agati-2002 for O. pratensis previously selected from preliminary screening trials based on resistant susceptible and intermediate trends towards pest infestation. Various physico-morphic and chemical plant characters viz., number of nodes per plant, plant height, cob height, stem diameter, length of central spike, cob length, leaf width, leaf trichomes, 100-gain weight, total dry matter, total minerals, crude protein, crude fats, neutral detergent fiber (NDF), acid detergent fiber (ADF), cellulose, lignin, nitrogen, phosphorus and potash were determined from the above mentioned selected genotypes of maize to correlate the role of these factors with the infestation caused by C. partellus and O. pratensis in their respective genotypes. The results indicated that all the physico-morphic factors showed significant differences among selected genotypes of maize crop and stem diameter, cob length, leaf width, leaf length, leaf trichomes and 100-grain weight showed negative and significant correlations with the pest infestation. Leaf trichomes showed maximum possible role (41.6%) in pest infestation fluctuations followed by stem diameter (32.7%). The role of all the physico-morphic plant characters when computed together showed a possible 84.8% contribution in pest infestation fluctuation. Most of the chemical plant factors were significantly different among selected genotypes. Among various chemical plant factors studied, total dry matter, total minerals, ADF, cellulose and potash showed significant and negative correlation with the plant infestation caused by C. partellus on 45 day old plants whereas, crude protein, nitrogen, potash and cellulose contents showed negative and significant correlation with the pest infestation on a 75 days old crop. Total dry matter showed maximum contribution in the pest infestation fluctuation i.e., 73.2 and 40.1% at 45 and 75 days old crop, respectively. Different physico-morphic and chemical plant characters studied for their correlation with leaf infestation caused by O. pratensis, showed significant variations among selected genotypes. Number of nodes, plant height, cob height, stem diameter, cob length and leaf length and length of central spike showed significant and negative correlation with the pest infestation. Leaf width, leaf trichomes and 100-grain weight were correlated nonsignificantly with the pest infestation. The coefficient of determination (100 R2) was calculated to be 82.0% when the effect of all the physico- morphic plant character was computed together on the pest infestation. Among chemical plant factors studied for their effect on leaf infestation caused by O. pratensis, total minerals, crude protein, crude fats, nitrogen, phosphorus and potash showed negative and significant correlation, whereas, neutral detergent fiber (NDF), acid detergent fiber (ADF), cellulose, lignin and total dry matter showed positive and significant correlation with the pest infestation. Total dry matter contributed 69.0% role in pest infestation fluctuation followed by crude protein with 7.9% role. The 100 R2 value was found to be 89.1% when the effect of all the chemical plant characters were computed together on the infestation fluctuation of the pest. Sustainable Pest Management Approaches for the Control of Maize Stem Borer and Mites. The study was conducted on sustainable management of Chilo partellus (Swinhoe) and Oligonychus pratensis (Banks) on selected genotypes of maize during the year 2005 and 2006. The effectiveness of various chemical and botanical insecticides and cultural practices were studied for the control of both the pests mentioned above during 2005. The most promising treatments were selected and tested for their effectiveness against C. partellus and O. pratensis in their possible integration combinations and net profitability with cost benefit ratios was determined. The results are summarized as under. Crown 75-WS (Imidacloprid), Furadan 3G (Carbofuron), Abamectin 10 EC, Cascade 10DC (Flufenoxuron), Karate 2.5 EC (Lambda cyhalothrin), Bifenthrin 20 EC, Neem (Azadirecta indica) seed powder and Chilies (Capsicum indicum) powder at 5 g/kg seed, 20 kg/ha, 750 ml/ha, 500 ml/ha, 625 ml/ha, 625 ml/ha, 10 kg/ha and 5 kg/ha, respectively were applied on susceptible maize genotype Sahiwal-2002 for the control of C. partellus during 2005. Furadan and Cascade were found to be most effective at all the post treatment intervals showing minimum plant infestation of 1.67% and with a reduction of 18.33% infestation over control. Various cultural practices viz. Post emergence weed control with Atrazine 38SC after 2nd irrigation, Pre-emergence weed control with Primextra Gold 720SC (Atrazine + S-Metachlor), Hand weeding at 5 plants stage of the crop and Hand weeding with hoeing at 5 plants stage were applied to determine their effect on infestation caused by C. partellus. None of the practices were found significantly effective. Due to the maximum yield observed under the practice of pre emergence weed control, it was selected as a best practice to be used in integrated management experiments. Pre emergence weed control, biological control and chemical control individually and in different combinations were applied during 2006 for the control of C. partellus. Combination of cultural, chemical and biological control resulted in minimum plant infestation (2.08%) and proved to be the best treatment followed by chemical + biological control with 2.18 % infestation. All the other treatments showed statistically equal response except pre-emergence weed control which showed maximum plant infestation (12.09%) caused by C. partellus. The resistant genotype (DK-6525) showed significantly minimum plant infestation (4.44%) as compared to susceptible genotype (SWL-2002) with 5.99 % plant infestation. The cost benefit ratio and net additional income of different management practices indicate that the maximum net additional income of Rupees 72125.00/ ha with an appreciable cost benefit ratio of 1:7.6 was estimated from those plots where cultural + chemical + biological control were integrated with resistant genotype DK- 6525. On the other hand the maximum cost benefit ratio of 1:27.9 with a net profit of Rs.71924.95/ ha was estimated from the plots with cultural + chemical control methods, whereas in susceptible genotype the same treatment resulted in 1: 16.67 CBR with maximum net profitability of Rs.41924.95/ ha. Post emergence weed control on a 40 day old crop + reduction of irrigation interval to 5 days resulted in minimum leaf infestation caused by O. pratensis i.e., 3.75 % and did not show significant variation with 4.17 and 5.0 % leaf infestation in those plots where reduction of irrigation interval to 5 days and pre-emergence weed control + reduction of irrigation intervals to 5 days were applied, respectively. The net additional profit was found to be maximum i.e., Rs.21465.00/ha in those plots where pre-emergence weed control and reduction of irrigation interval to 5 days were integrated with a cost benefit ratio of 1: 7.6 and hence proved to be the best." xml:lang="en_US