Awais Majeed

Towards Creation of Linguistic Resources for Bilingual Sentiment Analysis of Twitter Data

This paper presents an approach towards bi-lingual sentiment analysis of tweets. Social networks being most advanced and popular communication medium can help in designing better government and business strategies. There are a number of studies reported that use data from social networks; however, most of them are based on English language. In this research, we have focused on sentiment analysis of bilingual dataset (English and Roman-Urdu) on topic of national interest (General Elections). Our experiments produced encouraging results with 76% of tweet’s sentiment strength classified correctly. We have also created a bi-lingual lexicon that stores the sentiment strength of English and Roman Urdu terms. Our lexicon is available at: https://sites.google. com/a/mcs.edu.pk/codteem/biling_senti

Vocabulary of Quranic Concepts: A semi-automatically created terminology of Holy Quran

The identification and organization of terminology is the foremost step while organizing the domain knowledge for any domain as it is the terms and their inter-relationships that define the conceptual knowledge base. Quran, comprising the divine words of wisdom has been considered and used as prime source of knowledge and guidance for Muslims throughout the world for fourteen centuries. The concepts/topics discussed in Quran have been organized/indexed by many scholars which are used by Muslims who use them to search for guidance regarding various issues of daily life. In current era of information technology, various search services for Quranic topics are available online. They mostly use the terminologies (concepts hierarchy) manually built by scholars. In our work, we have used a semi-automatic approach to identify important concepts/topics from six English translations of Quran, and organized them into a hierarchical structure, named as Vocabulary of Quranic Concepts (VQC). CNC Value method of term recognition is used to identify significant concepts, which are then manually analyzed by domain expert, and are then organized into a hierarchy using the term-head principle. Due to extreme sensitivity of this work, complete automation of system is avoided and outcomes at all steps are manually analyzed. Currently, we have developed a vocabulary from translation of only second chapter of Quran (Al-Bakara). VQC is available at: https://sites.google.com/a/mcs.edu.pk/codteem/projects/qwn

Contributions to the study of bi-lingual Roman Urdu SMS spam filtering

With the increased usage of internet and mobile phones, number of spams has also increased in both these areas. The Spam in both these areas is an increasing threat and sometimes cause huge financial as well as data/confidentiality loss. Therefore, actions need to be taken to stop these spams on both media. This paper analyses various techniques that are currently being used in Spam filtering in the context of mobile text messages. The contents of SMS are unique in nature so some techniques might be effective while some might not be. Some of mostly used algorithms and techniques are discussed in this paper. Furthermore, we have performed automatic spam filtering using machine learning algorithms on Roman Urdu text messages and achieved an accuracy of 92.2% on a manually curated corpus of 8449 messages. The SMS corpus has also been made available for future research works.

A Survey of Evolution in Predictive Models and Impacting Factors in Customer Churn

The information-based prediction models using machine learning techniques have gained massive popularity during the last few decades. Such models have been applied in a number of domains such as medical diagnosis, crime prediction, movies rating, etc. Similar is the trend in telecom industry where prediction models have been applied to predict the dissatisfied customers who are likely to change the service provider. Due to immense financial cost of customer churn in telecom, the companies from all over the world have analyzed various factors (such as call cost, call quality, customer service response time, etc.) using several learners such as decision trees, support vector machines, neural networks, probabilistic models such as Bayes, etc. This paper presents a detailed survey of models from 2000 to 2015 describing the datasets used in churn prediction, impacting features in those datasets and classifiers that are used to implement prediction model. A total of 48 studies related to churn prediction in tel...

Analyzing Socio-economic and Geographical factors for Crime Incidents using Heat maps and Hotspots

Spatio-temporal data mining techniques are used for crime analysis for their knowledge oriented and meaningful visual representation of crime incidents. Visual representation of crime patterns assist analysts with in-depth understanding of crime behavior with time and location. The representation can be made more knowledgeable and perceptible by incorporating details of socio-economic factor and areafis geographical information providing insights to features that actually play role in certain crime pattern. To analyze the impact of these factors, two of the best density calculation clustering techniques i.e. Heat Maps and Hot Spots analysis are performed for Crime Against Person and Crime Against Property. The analysis demonstrated that Crimes Against Persons are more frequent in rural and sub-urban areas with mostly low socio-economic conditions; whereas, Crimes Against Property are mostly in commercial areas with mix socio-economic conditions.

Reputation Management System for Fostering Trust in Collaborative and Cohesive Disaster Management

The best management of a disaster requires knowledge, skills and other resources not only for relief and rehabilitation but also for recovery and mitigation of its effects. These multifaceted goals cannot be achieved by a single organization and require collaborative efforts in an agile manner. Blind trust cannot be applied while selecting collaborators/team members/partners therefore good reputation of a collaborator is mandatory. Currently, various Information and Communication Technology based artifacts, for collaborative disaster management, have been developed; however, they do not employ trust and reputation as their key factor. In this paper, a framework of reputation based trust management system is proposed for the support of disaster management. The key features of framework are Meta model, Reputation Indicator Matrix and Computational algorithm, deployed using Service Oriented Architecture. To evaluate the efficacy of the artifact, a prototype is implemented. Furthermore, an industrial survey is carried out to get the feedback on the proposed framework. The results support that the proposed reputation management system provides significant support in collaborative disaster management by assisting in agile and smart decision making in all phases of disaster management cycle.

Evaluation of Navigational Aspects of Moodle

Learning Management System (LMS) is an effective platform for communication and collaboration among teachers and students to enhance learning. These LMSs are now widely used in both conventional and virtual and distance learning paradigms. These LMSs have various limitations as identified in the existing literature, including poor learning content, use of appropriate technology and usability issues. Poor usability leads to the distraction of users. Literature covers many aspects of usability evaluation of LMS. However, there is less focus on navigational issues. Poor navigational can lead to disorientation and cognitive overload of the users of any Web application. For this reason, we have proposed a navigational evaluation framework to evaluate the navigational structure of the LMS. We have applied this framework to evaluate the navigational structure of Moodle. We conducted a survey among students and teachers of two leading universities in Pakistan, where Moodle is in use. This work summarizes the survey results and proposes guidelines to improve the usability of Moodle based on the feedback received from its users.

Volunteer Reputation evaluation for emergency response operations

Natural and man-made disasters are constantly occurring leading to human casualties, infrastructure destruction and financial losses. Volunteers and volunteer organizations play a significant role in each and every phase of disaster management. Therefore, selecting and retaining skilled, motivated and able volunteers becomes important. Existing ICT based solutions focus on resource allocation, team work and other disaster management activities, however none of these systems has addressed the issue of volunteers and their reputation. Reputation of a volunteer based on his personal traits and experience can be used for his selection for an emergency operation. It can also be used as a performance measurement tool during a particular operation. The current work proposes a reputation management system consisting of a Reputation Meta-model and a reputation system architecture for reputation management and measurement.

Using Crowd-Source Based Features from Social Media and Conventional Features to Predict the Movies Popularity

Predicting the success of movies has been of interest to economists and investors (media and production houses) as well as predictive analysts. A number of attributes such as cast, genre, budget, production house, PG rating affect the popularity of a movie. Social media such as Twitter, YouTube etc. are major platforms where people can share their views about the movies. This paper describes experiments in predictive analysis using machine learning algorithms on both conventional features, collected from movies databases on Web as well as social media features (text comments on YouTube, Tweets). The results demonstrate that the sentiments harnessed from social media and other social media features can predict the success with more accuracy than that of using conventional features. We achieved best value of 77% and 61% using selected social media features for Rating and Income prediction respectively, whereas selected conventional features gave results of 76.2% and 52% respectively. More it was found that the blend of both types of attributes (conventional and those collected from social media) can outperform the existing approaches in this domain.

A Novel Approach for Ranking Images Using User and Content Tags

In this study, a tag and content-based ranking algorithm is proposed for image retrieval that uses the metadata of images as well as the visual features of images, also known as “visual words” to retrieve more relevant images. Thus, making the retrieval process more accurate than the keyword-based retrieval approaches. Both tag and content-based image retrieval techniques have their own advantages and disadvantages. By combining the two, their disadvantages have been offset. The proposed system has been developed to bridge the gap between the existing techniques and the desired user requirements. Initially, the system extracts the metadata of images and stores them into a custom designed dictionary dataset. Then, the system creates a visual vocabulary and trains a classifier on a dataset of images belonging to different categories. Next, for any given userquery, the system makes a decision to display a class of images that best matches the query. These class images are processed in a way that we compute the relevance scores for each image and display the result based on the score.