Yasir Mehmood

Bio: Yasir Mehmood is an academic researcher. The author has contributed to research in topics: Lexicon & Sentiment analysis. The author has an hindex of 1, co-authored 2 publications receiving 1 citations.

An enhanced lexicon-based approach for sentiment analysis: a case study on illegal immigration

Abstract: Research on sentiment analysis were mostly conducted on product and services, resulting in scarcity of studies focusing on social issues, which may require different mechanisms due to the nature of the issue itself. This paper aims to address this gap by developing an enhanced lexicon-based approach.,An enhanced lexicon-based approach was employed using General Inquirer, incorporated with multi-level grammatical dependencies and the role of verb. Data on illegal immigration were gathered from Twitter for a period of three months, resulting in 694,141 tweets. Of these, 2,500 tweets were segregated into two datasets for evaluation purposes after filtering and pre-processing.,The enhanced approach outperformed ten online sentiment analysis tools with an overall accuracy of 81.4 and 82.3% for dataset 1 and 2, respectively as opposed to ten other sentiment analysis tools.,The study is novel in the sense that data pertaining to a social issue were used instead of products and services, which require different mechanism due to the nature of the issue itself.

Moving beyond Text Highlights: Inferring Users' Interests to Improve the Relevance of Retrieval.

Abstract: Introduction. Studies have indicated that users' text highlighting behaviour can be further manipulated to improve the relevance of retrieved results. This article reports on a study that examined users’ text highlight frequency, length and users' copy-paste actions. Method. A binary voting mechanism was employed to determine the weights for the feedback, which were then used to re-rank the original search results. A search engine prototype was built using the Communications of the ACM test collection, with the well-known BM25 acting as the baseline model. Analysis. The proposed enhanced model’s performance was evaluated using the mean average precisions and F-score metrics, and results were compared at the top 5, 10 and 15. Additionally, comparisons were also made based on the number of terms used in a query, that is single, double and triple terms. Results. The findings show that the enhanced model significantly outperformed BM25, and the rest of the models at all document levels. To be specific, the enhanced model showed significant improvements over the frequency model. Additionally, retrieval relevance was found to be the best when the query length is two. Conclusions. Users’ post-click behaviour may serve as a significant indicator of their interests, and thus can be used to improve the relevance of the retrieved results. Future studies could look into further extending this model by including other post-click behaviour such as printing or saving.

Automatic Short Answer Grading With SemSpace Sense Vectors and MaLSTM

Abstract: Automatic assessment of exams is widely preferred by educators than multiple-choice exams because of its efficiency in measuring student performance, lack of subjectivity when evaluating student response, and faster evaluation time than the time consuming manual evaluation. In this study, a new approach for the Automatic Short Answer Grading (ASAG) is proposed using MaLSTM and the sense vectors obtained by SemSpace, a synset based sense embedding method built leveraging WordNet. Synset representations of the Student’s answers and reference answers are given as input into parallel LSTM architecture, they are transformed into sentence representations in the hidden layer and the vectorial similarity of these two representation vectors are computed with Manhattan Similarity in the output layer. The proposed approach has been tested using the Mohler ASAG dataset and successful results are obtained in terms of Pearson (r) correlation and RMSE. Also, the proposed approach has been tested as a case study using a specific dataset (CU-NLP) created from the exam of the “Natural Language Processing” course in the Computer Engineering Department of Cukurova University. And it has achieved a successful correlation. The results obtained in the experiments show that the proposed system can be used efficiently and effectively in context-dependent ASAG tasks.

Analysing the sentiments about the education system trough Twitter

Abstract: This paper applies Information and Communication Technologies (ICT) as well as data analysis to gain a better understanding of the existing perception on the education system. 45,278 tweets were downloaded and processed. Using a lexicon-based approach, examining the most frequently used words, and estimating similarities between terms, we detected that a predominantly negative perception of the education system exists in most of the analysed countries. A positive perception is identified in certain low-income nations. Men exhibit a more positive sentiment than women as well as a higher subjectivity in some countries. The countries that exhibit the most positive perceptions India, Canada, Pakistan, Australia, South Africa and Kenya are also those that manifest the highest subjectivity.

Sentiment analysis on social media tweets using dimensionality reduction and natural language processing

Abstract: Social media has been embraced by different people as a convenient and official medium of communication. People write or share messages and attach images and videos on Twitter, Facebook and other social media platforms. It therefore generates a lot of data that is rich in sentiments. Sentiment analysis has been used to determine the opinions of clients, for instance, relating to a particular product or company. Lexicon and machine learning approaches are the strategies that have been used to analyze these sentiments. The performance of sentiment analysis is, however, distorted by noise, the curse of dimensionality, the data domains and the size of data used for training and testing. This article aims at developing a model for sentiment analysis of social media data in which dimensionality reduction and natural language processing with part of speech tagging are incorporated. The model is tested using Naïve Bayes, support vector machine, and K‐nearest neighbor algorithms, and its performance compared with that of two other sentiment analysis models. Experimental results show that the model improves sentiment analysis performance using machine learning techniques.

Sentiment Analysis Techniques and their Uses: An Analytical Study

Abstract: Sentiment Analysis has become a centre of attraction in context of natural language processing and text mining lately. Modern complex businesses use it as an effective marketing strategy where goods are traded over internet and buyers leave their feedbacks. The paper presents a systematic analysis of the highly referred methods and methodologies that are implemented to conduct Sentiment Analysis and recommends the most effective ways to use them. The paper takes an illustration from a Bollywood movie “Drishyam2’’ to employ Sentiment Analysis on the viewers.