Muhammad Iqbal Abu Latiffi

Bio: Muhammad Iqbal Abu Latiffi is an academic researcher from National University of Malaysia. The author has contributed to research in topics: Sentiment analysis & Machine learning. The author has an hindex of 2, co-authored 3 publications receiving 7 citations.

A Review on Sentiment Analysis Techniques and Applications

Abstract: Nowadays, what user think is the most difficult and complicated task handled by organizations. The way to idetify the attitude of the speaker or a writer on some topics is to use sentiment analysis. The use of sentiment analysis is to identify user's opinion towards some topics whether it is positive or negative. This paper presents the techniques used by previous researchers in sentiment analysis which are Machine Learning and Natural Language Processing (NLP) in solving the classification task. The comparison among these two main approaches reveals that Machine Learning techniques can solve classification task with reasonable success and with very high accuracy compared to NLP-based techniques but it is depending on the training and test data with respect to the domain. This paper also presents the use of ontology in sentiment analysis that can help in achieving more high accuracy for the classification task.

Sentiment Analysis: An Enhancement of Ontological-Based Using Hybrid Machine Learning Techniques

Abstract: With the fast development of World Wide Web 2.0 has resulted in huge number of reviews where the consumers share their opinion about a variety of products in the websites, forum and social media such as Twitter and Instagram. For the organizations, they have to analyze customer’s behavior to find new market trends and insights. Sentiment analysis concept used to extract the positive, negative or neutral sentiment of the features from the unstructured data of product reviews. In this paper, we explore the techniques and tools used to enhance the ontology-based approach. Combination of ontology-based on Formal Concept Analysis (FCA) which a process of obtaining a formal ontology or a concept hierarchy from a group of objects with their properties and K-Nearest Neighbor (KNN) to classify the reviews. We believe with these techniques, we are able to view the strength and weakness of the product in more detail where the feature selection process will more be systematic and will result in the highest feature set.

Sentiment analysis of preschool teachers’ perceptions on ICT use for young children

Abstract: Sentiment analysis in gaining more attention as it is increasingly used in multiple domains, including in interpreting educational data. The article uses sentiment analysis technique to understand the early childhood educators reported beliefs (perception) on young children’s ICT use. The dataset was obtained from a comparative study of early childhood educators from two countries, Australia and Malaysia. The result shows a similar outcome where most teachers agreed upon the benefits of ICT use and conclude more positive sentiment polarity.This paper summarizes the findings using sentiment analysis as well as comparing it to the quantitative data obtained from the survey.

Flower Pollination Algorithm for Feature Selection in Tweets Sentiment Analysis

Abstract: —Text-based social media platforms have developed into important components for communication between customers and businesses. Users can easily state their thoughts and evaluations about products or services on social media. Machine learning algorithms have been hailed as one of the most efficient approaches for sentiment analysis in recent years. However, as the number of online reviews increases, the dimensionality of text data increases significantly. Due to the dimensionality issue, the performance of machine learning methods has been degraded. However, traditional feature selection methods select attributes based on their popularity, which typically does not improve classification performance. This work presents a population-based metaheuristic for feature selection algorithms named Flower Pollination Algorithms (FPA) because of their propensity to accept less optimum solutions and avoid getting caught in local optimum solutions. The study analyses tweets from Kaggle first with the usual Term Frequency-Inverse Document Frequency statistical weighting filter and then with the FPA. Four baseline classifiers are used to train the features: Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN). The results demonstrate that the FPA outperforms alternative feature subset selection algorithms. For the FPA, an average improvement in accuracy of 2.7% is seen. The SVM achieves a better accuracy of 98.99%.

Aspect-Based Sentiment Analysis Methods in Recent Years

Abstract: Sentiment Analysis (SA) is the computational treatment of opinions, sentiments and subjectivity of text. Aspect-based Sentiment Analysis (ABSA) is a specific SA that aims to extract most important aspects of an entity and predict the polarity of each aspect from the text. A review of the recent state-of-the-art in ABSA, shows the remarkable growing in finding both aspect, and the corresponding sentiment. Current methods are categorized based on their proposed algorithms and models. For each discussed study, aspect extraction method and sentiment prediction method, the dataset, domain and the reported performance is included. The main goal of this work is to review ABSA techniques with brief details. The main contributions of this paper consist of the refined categorizations of a great number of recent articles, comparing them and the illustration of the recent trend of research in the ABSA.

Text Classification based Behavioural Analysis of WhatsApp Chats

Abstract: WhatsApp is used by millions of users to express emotions and share feelings. The model is presented in this paper aims to perform sentimental and emotional analysis using textual messages and emojis used in WhatsApp chats. Code switching, which is quite prevalent over online conversations, is handled by the model by unifying and converting all the texts to a standard form. For each subject, multiple chats are taken; translated and using a neural network, each sentence and emoji is scored in a dimensional form. The composition of the emotions expressed by the subject (out of Happy, Sad, Bored, Fear, Anger and Excitement) are defined. The scores are added up for each subject. Throughout the analysis, the behavioral traits are extracted. It is determined that, if the subject likes to use emojis and if they use it as a replacement for words or as an add-on to express their emotions better. It is also observed that if the subject behaves differently on text according to the person in front of them with regard to these emotions and finally, if the subject is an introvert or extrovert.

PackerRobo: Model-based robot vision self supervised learning in CART

Abstract: Robots are most widely used to replace human contribution with machine generated response. When humans interact with robots, its mandatory for both to forecast actions based on current conditions. Huge efforts have been channelized towards attaining this perfect coordination. To decipher complex environments, the inference of robotic mobility and alteration of random unstructured scenarios is a complicated task in the field of visual processing and imaging. To address this issue, a new Vision-Based Interaction Model based on deep neural networks has been suggested. The proposed model solves the error amplification issue by the application of past inputs through features as reposed by a Deep Belief Network (DBN). In addition, a novel Vision-Based Robotics Learning model is also proposed for scene understanding and recognition using deep neural network understanding. Moreover, a vision theory-based smart learning algorithm is also suggested to decide positive possible outcomes.Therefore, the model is capable of using object motions to extract relevant information used for Turning, Griping and object mobility.To validate the suggested model, a number of experiments have been performed on benchmark datasets and it showed a higher performance as evaluated against some of the niche methods.

Integration of opinion into customer analysis model

Abstract: As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows rapidly. In order to enhance customer satisfaction and their shopping experiences, it has become important to analysis customers reviews to extract opinions on the products that they buy. Thus, Opinion Mining is getting more important than before especially in doing analysis and forecasting about customers’ behavior for businesses purpose. The right decision in producing new products or services based on data about customers’ characteristics means profit for organization/company. This paper proposes a new architecture for Opinion Mining, which uses a multidimensional model to integrate customers’ characteristics and their comments about products (or services). The key step to achieve this objective is to transfer comments (opinions) to a fact table that includes several dimensions, such as, customers, products, time and locations. This research presents a comprehensive way to calculate customers’ orientation for all possible products’ attributes.