Anthoniraj Amalanathan

Bio: Anthoniraj Amalanathan is an academic researcher from VIT University. The author has contributed to research in topics: Social network & Semantic Web. The author has an hindex of 4, co-authored 13 publications receiving 38 citations.

Probabilistic Unsupervised Machine Learning Approach for a Similar Image Recommender System for E-Commerce

Abstract: The recommender system is the most profound research area for e-commerce product recommendations. Currently, many e-commerce platforms use a text-based product search, which has limitations to fetch the most similar products. An image-based similarity search for recommendations had considerable gains in popularity for many areas, especially for the e-commerce platforms giving a better visual search experience by the users. In our research work, we proposed a machine-learning-based approach for a similar image-based recommender system. We applied a dimensionality reduction technique using Principal Component Analysis (PCA) through Singular Value Decomposition (SVD) for transforming the extracted features into lower-dimensional space. Further, we applied the K-Means++ clustering approach for the possible cluster identification for a similar group of products. Later, we computed the Manhattan distance measure for the input image to the target clusters set for fetching the top-N similar products with low distance measure. We compared our approach with five different unsupervised clustering algorithms, namely Minibatch, K-Mediod, Agglomerative, Brich, and the Gaussian Mixture Model (GMM), and used the 40,000 fashion product image dataset from the Kaggle web platform for the product recommendation process. We computed various cluster performance metrics on K-means++ and achieved a Silhouette Coefficient (SC) of 0.1414, a Calinski-Harabasz (CH) index score of 669.4, and a Davies–Bouldin (DB) index score of 1.8538. Finally, our proposed PCA-SVD transformed K-mean++ approach showed superior performance compared to the other five clustering approaches for similar image product recommendations.

A review on user influence ranking factors in social networks

Abstract: Social networks play a significant role in information sharing and have become an essential part of user's daily activities. Social networks help share users' ideas, views, status and opinions in the form of text, music and videos. The inherent difficulties involved in sharing the information is the sustenance of the values attached to the dependability of the functional blocks of the user - identity, sharing, conversation, relationship, presence, group and reputation. Review of social networks in terms of user influence ranking would throw light on the role of these functional blocks. The user influence ranking generally reveals the impact that an individual has on the social network. In the present scenario, the user influence ranking factors are not systematically determined. Instead, each social network adopts its own method to determine users' influence. Hence, the review has been done to identify the adoption of these functional blocks in popular social networks to determine users' influence ranking method.

A Framework for E-Governance System using Linked Data and Belief-desire-intention Agent

Abstract: E-Governance systems are built for the government to interact with citizens and efficiently provide workflow between the organizations. These systems play major role in efficiently organizing the government knowledge and enabling citizen friendly services. Traditionally E-Governance systems are developed as a requirement basis trend, where the requirement of establishing a service is evaluated and a system for that particular requirement is deployed. A framework has been introduced to develop an E-Governance system in an evolutionary fashion where the core government model is deployed and further services are deployed over the core. The key element in achieving such evolutionary system is by adding semantics to the knowledge which is represented in the form of Linked Data.

Social Network User’s Content Personalization based on Emoticons

Abstract: The social networks help sharing user’s multidimensional content which includes text, image, audio and video at any time. Emoticons are helpful in precise content sharing as an alternative of text and need to be analyzed for sharing of the right content. The content being shared mostly reflects the behavioral characteristics of the users and imitates their emotions.Therefore, each emoticon needs to be mapped with standard emotions. The emoticons proposed by Unicode consortium are considered and mapped with nine basic emotions such as love, happiness, pity, furious, heroic, fearful, disgust, wonder and peace. A prediction model based on decision tree classifier is designed to classify user’s contentaccording to the emotions expressed through the emoticons, especially for tweets. The designed methodology is demonstrated using two thousand tweets. Tweets are adopted for its simplicity and limited processing with only hundred and forty characters. The outcome obtained by applying the designed methodology provided satisfactory results of 83% accuracy which is more than the average accuracy (75%) of standard machine learning classification process. Therefore, it is possible to guess the behavior of the users through sharing the different forms of emoticons at various instances. This classification of users’ content would reflect the dominant emotions possessed by them. This finding helps in understanding the basic nature of an individual in social networks. Having identified the basic nature of an individual through emoticons, it is very easy to personalize the user’s social network page to filter disinterested and disgusting content at any time.

e-SimNet: a visual similar product recommender system for E-commerce

Abstract: Visual similarity recommendations have an immense role in e-commerce portals. Fetching the appropriate similar products and suggesting to the buyers based on the product image's visual features is complex. Here in our research, we presented an efficient e-commerce similar product network model (e-SimNet) for visually similar recommendations. To achieve our objective, we have performed image feature extraction and generating embeddings using deep learning techniques and built an Index tree using the approximate nearest neighbor oh Yeah (Annoy) algorithm. Further, we have fetches top-N the near similar items using distance measure. We have benchmarked our model in terms of Accuracy, Error rate, and results show that better than other state-of-the-art approaches with 96.22% of accuracy.

Sentiment of Emojis.

Abstract: There is a new generation of emoticons, called emojis, that is increasingly being used in mobile communications and social media. In the past two years, over ten billion emojis were used on Twitter. Emojis are Unicode graphic symbols, used as a shorthand to express concepts and ideas. In contrast to the small number of well-known emoticons that carry clear emotional contents, there are hundreds of emojis. But what are their emotional contents? We provide the first emoji sentiment lexicon, called the Emoji Sentiment Ranking, and draw a sentiment map of the 751 most frequently used emojis. The sentiment of the emojis is computed from the sentiment of the tweets in which they occur. We engaged 83 human annotators to label over 1.6 million tweets in 13 European languages by the sentiment polarity (negative, neutral, or positive). About 4% of the annotated tweets contain emojis. The sentiment analysis of the emojis allows us to draw several interesting conclusions. It turns out that most of the emojis are positive, especially the most popular ones. The sentiment distribution of the tweets with and without emojis is significantly different. The inter-annotator agreement on the tweets with emojis is higher. Emojis tend to occur at the end of the tweets, and their sentiment polarity increases with the distance. We observe no significant differences in the emoji rankings between the 13 languages and the Emoji Sentiment Ranking. Consequently, we propose our Emoji Sentiment Ranking as a European language-independent resource for automated sentiment analysis. Finally, the paper provides a formalization of sentiment and a novel visualization in the form of a sentiment bar.

User Interface Plasticity: Model Driven Engineering to the Limit!

Abstract: Ten years ago, I introduced the notion of user interface plasticity to denote the capacity of user interfaces to adapt, or to be adapted, to the context of use while preserving usability. The Model Driven Engineering (MDE) approach, which was used for user interface generation since the early eighties in HCI, has recently been revived to address this complex problem. Although MDE has resulted in interesting and convincing results for conventional WIMP user interfaces, it has not fully demonstrated its theoretical promises yet. In this paper, we discuss how to push MDE to the limit in order to reconcile high-level modeling techniques with low-level programming in order to go beyond WIMP user interfaces.

CredSaT: Credibility ranking of users in big social data incorporating semantic analysis and temporal factor:

Abstract: The widespread use of big social data has influenced the research community in several significant ways. In particular, the notion of social trust has attracted a great deal of attention from infor...

Time-aware domain-based social influence prediction

Abstract: Online social networks have established virtual platforms enabling people to express their opinions, interests and thoughts in a variety of contexts and domains, allowing legitimate users as well as spammers and other untrustworthy users to publish and spread their content. Hence, it is vital to have an accurate understanding of the contextual content of social users, thus establishing grounds for measuring their social influence accordingly. In particular, there is the need for a better understanding of domain-based social trust to improve and expand the analysis process and determining the credibility of Social Big Data. The aim of this paper is to determine domain-based social influencers by means of a framework that incorporates semantic analysis and machine learning modules to measure and predict users’ credibility in numerous domains at different time periods. The evaluation of the experiment conducted herein validates the applicability of semantic analysis and machine learning techniques in detecting highly trustworthy domain-based influencers.

From Emojis to Sentiment Analysis

Abstract: Studies on Twitter are becoming quite common these years. Even so, the majority of them did not focused on emoticons, even less on emojis. An overview of emoticons related work has been made recently [11]. However there is still too little research work related to emojis. In this paper we draw up the work and future approaches worth considering for emoji usage in Sentiment Analysis. We aim to put necessary theoretical background before using emojis for sentiment analysis. Thus, we present an emoji usage typology along with linguistic and socio-linguistic studies on the interpretation of emojis. We also introduce approaches exploiting emojis in Sentiment Analysis. We conclude by presenting our perspectives in this domain considering the evolution of emoji usages.