Nikola S. Nikolov

Verified

Nikola verified their affiliation via an institutional email.

Learn more

Verified

Nikola verified their affiliation via an institutional email.

Learn more

• PhD in Computer Science
• Associate Professor at University of Limerick

With the development of ubiquitous computing, recommendation systems have become essential tools in assisting users in discovering services they would find interesting. This process is highly dynamic with an increasing number of services, distributed over networks, bringing the problems of cold start and sparsity for service recommendation to a new...

We introduce a new graph drawing convention for 3D hierarchical drawings of directed graphs. The vertex set is partitioned into layers of vertices drawn in parallel planes. The vertex set is further partitioned into k>=2 subsets, called walls. The layout consists of a set of parallel walls which are perpendicular to the set of parallel planes of th...

We introduce a new force-directed graph drawing algorithm for large undirected graphs with at least a few hundreds of vertices. Our algorithm falls into the class of multilevel force-directed graph drawing algorithms. Unlike other multilevel algorithms it has no pre-processing step and it also ignores repulsion forces between pairs of non-adjacent...

Generative language modelling has surged in popularity with the emergence of services such as ChatGPT and Google Gemini. While these models have demonstrated transformative potential in productivity and communication, they overwhelmingly cater to high-resource languages like English. This has amplified concerns over linguistic inequality in natural...

Natural Language Processing (NLP) is becoming a dominant subset of artificial intelligence as the need to help machines understand human language looks indispensable. Several NLP applications are ubiquitous, partly due to the myriads of datasets being churned out daily through mediums like social networking sites. However, the growing development h...

The rapid growth of textual data on the web has led researchers to develop methods in Natural Language Processing (NLP) to process, understand, and identify topics... Among these methods, Topic Modeling helps extract relevant topics, represented as clusters of words. However, interpreting these clusters into meaningful topics remains a challenge. T...

Recent efforts to understand intermediate representations in deep neural networks have commonly attempted to label individual neurons and combinations of neurons that make up linear directions in the latent space by examining extremal neuron activations and the highest direction projections. In this paper, we show that this approach, although yield...

Within the Hadoop ecosystem, MapReduce stands as a cornerstone for managing, processing, and mining large-scale datasets. Yet, the absence of efficient solutions for precise estimation of job execution times poses a persistent challenge, impacting task allocation and distribution within Hadoop clusters. In this study, we present a comprehensive mac...

Accurate racism classification is crucial on social media, where racist and discriminatory content can harm individuals and society. Automated racism detection requires gathering and annotating a wide range of diverse and representative data as an essential source of information for the system. However, this task proves to be highly demanding in bo...

Electronic health records (EHRs) are a critical tool in healthcare and capture a wide array of patient information that can inform clinical decision-making. However, the sheer volume and complexity of EHR data present challenges for healthcare providers, particularly in fast-paced environments such as intensive care units (ICUs). To address this pr...

Our study addresses a significant gap in online hate speech detection research by focusing on homophobia, an area often neglected in sentiment analysis research. Utilising advanced sentiment analysis models, particularly BERT, and traditional machine learning methods, we developed a nuanced approach to identify homophobic content on X/Twitter. This...

Our study addresses a significant gap in online hate speech detection research by focusing on homophobia, an area often neglected in sentiment analysis research. Utilising advanced sentiment analysis models, particularly BERT, and traditional machine learning methods, we developed a nuanced approach to identify homophobic content on X/Twitter. This...

This paper presents a comparison between various text vectorization and machine learning algorithms for solving the problem of detection of racism on multi-lingual social media. We train classification models on Facebook comments and tweets in three different languages: English, French and Arabic. Our findings suggest that for the English-language...

Hadoop MapReduce is a well-known open source framework for processing a large amount of data in a cluster of machines; it has been adopted by many organizations and deployed on-premise and on the cloud. MapReduce job execution time estimation and prediction are crucial for efficient scheduling, resource management, better energy consumption, and co...

Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford’s law, as a method used to quantify the differenc...

Although different studies are carried out by deep learning models for financial markets sentiment analysis, there is a lack of specific embedding method that regards the domain. Therefore, the goal of this study is to discover what type of embedding techniques along with different classification algorithms work better for the financial markets’ se...

Background: In recent years, social media has become a major channel for health-related information in Saudi Arabia. Prior health informatics studies have suggested that a large proportion of health-related posts on social media are inaccurate. Given the subject matter and the scale of dissemination of such information, it is important to be able...

BACKGROUND In recent years, social media has become a major channel for health-related information in Saudi Arabia. Prior health informatics studies have suggested that a large proportion of health-related posts on social media are inaccurate. Given the subject matter and the scale of dissemination of such information, it is important to be able to...

This paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets...

Collaborative filtering (CF) has achieved great success in the field of recommender systems. In recent years, many novel CF models, particularly those based on deep learning or graph techniques, have been proposed for a variety of recommendation tasks, such as rating prediction and item ranking. These newly published models usually demonstrate thei...

Deep learning models are now considered state-of-the-art in many areas of pattern recognition. In speaker recognition, several architectures have been studied, such as deep neural networks (DNNs), deep belief networks (DBNs), restricted Boltzmann machines (RBMs), and so on, while convolutional neural networks (CNNs) are the most widely used models...

Matrix Factorization (MF) is one of the most successful Collaborative Filtering (CF) techniques used in recommender systems due to its effectiveness and ability to deal with very large user-item rating matrix. However, when the rating matrix sparseness increases its performance deteriorates. Expanding MF to include side-information of users and ite...

This era is witnessing a great and rapid development in the field of communications and informatics, that including the use of the Internet and social media platforms, these platforms are witnessing unprecedented use in the last two decades. This use is the way people interact with each other. There is no doubt that this interaction has a positive...

This paper presents the results of several ML experiments, conducted with a dataset of YouTube comments in Arabic. The experiments aim at studying the impact of various text pre-processing, feature-extraction and feature-selection techniques on the accuracy of a document classifier for detection of offensive language in online communication in Arab...

In the era of global-scale services, organisations produce huge volumes of data, often distributed across multiple data centres, separated by vast geographical distances. While cluster computing applications, such as MapReduce and Spark, have been widely deployed in data centres to support commercial applications and scientific research, they are n...

Collaborative filtering (CF) has achieved great success in the field of recommender systems. In recent years, many novel CF models, particularly those based on deep learning or graph techniques, have been proposed for a variety of recommendation tasks, such as rating prediction and item ranking. These newly published models usually demonstrate thei...

The Dimensionality Curse is one of the most critical issues that are hindering faster evolution in several fields broadly, and in bioinformatics distinctively. To counter this curse, a conglomerate solution is needed. Among the renowned techniques that proved efficacy, the scaling-based dimensionality reduction techniques are the most prevalent. To...

We propose a novel usage of convolutional neural networks (CNNs) for the problem of speaker recognition. While being particularly designed for computer vision problems, CNNs have recently been applied for speaker recognition by using spectrograms as input images. We believe that this approach is not optimal as it may result in two cumulative errors...

This paper presents a novel matrix factorization (MF) recommendation model, FeatureMF, which extends item latent vectors with item representation learned from metadata. By taking into account item features, the model addresses the coldstart item problem and data-sparsity problem of collaborative filtering (CF). Extensive experiments conducted on a...

This paper presents a novel matrix factorization (MF) model, called FeatureMF, which takes into account item features and thus addresses the cold-start item and data sparsity problems of collaborative filtering (CF). More specifically, the model extends item latent vectors with item representation learned from metadata. Experiments conducted on a p...

Background: Social media platforms play a vital role in the dissemination of health information. However, evidence suggests that a high proportion of Twitter posts (ie, tweets) are not necessarily accurate, and many studies suggest that tweets do not need to be accurate, or at least evidence based, to receive traction. This is a dangerous combinati...

Offensive content on social media such as verbal attacks, demeaning comments or hate speech has many negative effects on its users. The automatic detection of offensive language on Arabic social media is an important step towards the regulation of such content for Arabic speaking users of social media. This paper presents the results of evaluating...

Abstract In the era of accelerating growth of genomic data, feature-selection techniques are believed to become a game changer that can help substantially reduce the complexity of the data, thus making it easier to analyze and translate it into useful information. It is expected that within the next decade, researchers will head towards analyzing t...

We present the results of predictive modelling for the detection of anti-social behaviour in online communication in Arabic, such as comments which contain obscene or offensive words and phrases. We collected and labelled a large dataset of YouTube comments in Arabic which contains a broad range of both offensive and inoffensive comments. We used t...

Warning: this paper contains a range of words which may cause offence. In recent years, many studies target anti-social behaviour such as offensive language and cyberbullying in online communication. Typically, these studies collect data from various reachable sources, the majority of the datasets being in English. However, to the best of our knowl...

We consider the question of whether a given graph drawing \(\varGamma \) of a triconnected planar graph G is a weighted barycenter drawing. We answer the question with an elegant arithmetic characterisation using the faces of \(\varGamma \). This leads to positive answers when the graph is a Halin graph, and to a polynomial time recognition algorit...

The publication presents the results of empirical research on web technologies used in the home pages of the Finland commercial banks authorized under Finland Legislation to carry on commercial banking business and supervised by the Finland Financial Supervisory Authority (FIN-FSA). The home pages of 9 commercial banks were studied. Our survey reve...

We consider the question of whether a given graph drawing $\Gamma$ of a triconnected planar graph $G$ is a weighted barycenter drawing. We answer the question with an elegant arithmetic characterisation using the faces of $\Gamma$. This leads to positive answers when the graph is a Halin graph, and to a polynomial time recognition algorithm when th...

The goal of our study is to develop techniques based on Natural Language Processing (NLP) for detection of offensive language on a social media platform. This work aims at identifying the characterristics of the language generated on social media by Arabs from multiple countries in the Arab region, and finding proper solutions based on machine lear...

NetvizGL is a C++ OpenGL application for the visualisation of network graphs. It is a lightweight application designed to be minimal, extensible and scalable. NetvizGL can draw networks per a set of graph drawing algorithms. These algorithms are either be pre-packaged or a user may choose to write their own. With an an adaptation mechanism in place...

Semantic Recommendation Prototype Adapted for the Ubiquitous Consumer Wireless World

With the rapid growth of the Web, recommender systems have become essential tools to assist users to find high-quality personalized recommendations from massive information resources. Content-based filtering (CB) and collaborative filtering (CF) are the two most popular and widely used recommendation approaches. In this paper, we focus on ways of t...

Recommendation systems employed on the Internet aim to serve users by recommending items which will likely be of interest to them. The recommendation problem could be cast as either a rating estimation problem which aims to predict as accurately as possible for a user the rating values of items which are yet unrated by that user, or as a ranking pr...

This study focuses on the performance improving of social assisted search by using the Redis system as a cache layer between an application and a MySQL system which stores data extracted from the behavior of many users. Since searches made by one particular user can be viewed as a Markov chain, there is need for a lot of data to be read and display...

This paper proposes an improvement to item recommendation systems based on collaborative filtering (CF) with implicit feedback data. Combined with the Bayesian Personalized Ranking (BPR) optimization approach, recommended for implicit-only feedback contexts, CF has been shown to be effective in generating accurate recommendations. The method, based...

In recent years, there has been significant growth in the uptake of personal communication technologies across the world. This has been largely afforded by the wide availability of social media (SM) and facilitated by the increase in smartphone ownership. However, this growth does not come without disadvantages. For example, there is growing eviden...

Exploiting additional item meta-data is proposed in this paper for solving data sparsity and cold start problems found in item-based collaborative filtering (CF) techniques, which are employed in recommendation systems. Additional item meta-data provides the foundation for generating a heterogeneous information network (HIN). The proposed approach...

This paper describes the general service recommendation process matched to the telecommunication service delivery characteristics of the Ubiquitous Consumer Wireless World (UCWW). The goal is to provide consumers with the `best' service instances that match their dynamic, contextualized and personalized requirements and expectations, thereby aligni...

The item-based collaborative filtering (CF) is one of the most successful approaches utilized by the recommendation systems. The basic concept behind it is to recommend those items to users which are similar to other items that these users have been interested in recently. This paper proposes a hybrid method that integrates user trust relations wit...

We report on our findings using a genetic algorithm (GA) as a preprocessing step for force-directed graph drawings to find a smart initial vertex layout (instead of a random initial layout) to decrease the number of edge crossings in the graph. We demonstrate that the initial layouts found by our GA improve the chances of finding better results in...

We report on our findings using Simulated Annealing (SA) as a preprocessing step for force-directed graph drawing. Our proposed SA algorithm finds a smart initial vertex placement (instead of a random initial vertex placement) in order to decrease the chance of having edge crossings (local minima) and also to decrease the number of required iterati...

Context-aware recommendation systems make recommendations by adapting to user's specific situation, and thus by exploring both the user preferences and the environment. In this paper, we propose a context-aware service recommendation framework utilising semantic knowledge in the Ubiquitous Consumer Wireless World (UCWW). The main objective of the f...

We introduce a force-directed algorithm, called Sync-and-Burst, which falls into the category of classical force-directed graph drawing algorithms. A distinct feature in Sync-and-Burst is the use of simplified forces of attraction and repulsion whose magnitude does not depend on the distance between vertices. Instead, magnitudes are uniform through...

We propose a genetic algorithm (GA) for solving the maximization version of the Optimal Linear Arrangement problem and we also demonstrate how solutions found by it can be used for constructing smart initial layouts for force-directed graph drawing. Effectively, we show that our GA can be used as a first step in force-directed graph drawing for ach...

Context-aware recommendation systems make recommendations by adapting to user's specific situation, and thus by exploring both the user preferences and the environment. In this paper, the design of a context-aware service recommendation framework utilising semantic knowledge in the Ubiquitous Consumer Wireless World (UCWW) is outlined. The main obj...

The exponential growth of various social media platforms in recent years has created the opportunity for people to interact and communicate with each other to a degree unprecedented before the invention of the Web. This development is without doubt beneficial for society; however, it has also been associated with an escalation of cyberbullying acti...

With software development becoming a very popular hobby and career for many, the range of technologies and programming languages that are available today is very wide and diverse; each language being crafted for certain problem areas. The goal of this project is to utilise the public data available in a large online source control system for creati...

We present an algorithm which produces circular-shape layouts of trees by simulating synchronisation dynamics on the tree. Our approach consists of evolving scalar dynamical values assigned to the nodes. Then the dissimilarities between the values of each pair of nodes are utilised to calculate the coordinates of the nodes by using a lower bound on...

This paper describes research into a new cloud-based service recommendation system for the Ubiquitous Consumer Wireless World (UCWW). The main objective of the system is to provide users with the 'best' service instances that match their dynamic, contextualised and personalised requirements and expectations, thereby achieving the goal of the always...

The aim of this report is to review existing technologies in the area of big data and information visualisation with a view to narrowing the focus of the author's research project. The preliminary concept of this project is to investigate whether it is possible to define an effective way for people to search for patterns in a large dataset as well...

We present a visualization technique for radial drawing of trees consisting of two slightly different algorithms. Both of them make use of node-link diagrams for visual encoding. This visualization creates clear drawings without edge crossing. One of the algorithms is suitable for real-time visualization of large trees, as it requires minimal recal...

This paper describes the design and development of a novel cloud-based system for increased service contextualization in future wireless networks. The principal objective is the support of mobile users (consumers) in a Ubiquitous Consumer Wireless World (UCWW) seeking to choose and select the ‘best’ service instance in a UCWW environment matched to...

Abstract: Recent years have seen the relatively staid and conservative environment of the museum access the potential that is the new wave of new technologies incorporating Web 2.0, the Social Web, Netknowing and Net Collaborative Practices for collaboration and ubiquitous learning. Some – only a few, as of yet - have embraced the use of 3D game te...

A wireless solution for context- and service-awareness in mobile communications is the theme of this paper. Respecting mobile users’ desire for minimal intrusion of unsolicited advertisements, here we show how the novel push-advertisement technology and medium of ‘wireless billboard channels’ (WBCs) could be employed by service providers to broadca...

This paper presents various methods for visualization and analysis of email networks; visualization on the surface of a sphere to reveal communication patterns between different groups, a hierarchical drawing displaying the centrality analysis of nodes to emphasize important nodes, a 2.5D visualization for temporal email networks to analyze the evo...

We introduce a new graph drawing convention for 2.5D hierarchical drawings of directed graphs. The vertex set is partitioned both into layers of vertices drawn in parallel planes and into k � 2 subsets, called walls, and also drawn in parallel planes. The planes of the walls are perpen- dicular to the planes of the layers. We present a method for c...

This paper presents the design and implementation of an ant colony optimization based algorithm for solving the DAG layering problem. This algorithm produces compact layerings by minimising their width and height. Importantly it takes into account the contribution of dummy vertices to the width of the resulting layering.

This poster presents various methods for visualization and analysis of small-world email networks with various perspectives: vi-sualization on the surface of a sphere to reveal the relationships between different groups, a 2.5D hierarchical visualization method combined with the centrality value of nodes to analyze important people, a 2.5D visualiz...

This work contributes to the wide research area of visualization of hierarchical graphs. We present a new polynomial-time heuristic which can be integrated into the Sugiyama method for drawing hierarchical graphs. Our heuristic, which we call Promote Layering (PL), is applied to the output of the layering phase of the Sugiyama method. PL is a simpl...

This paper describes the GEOMI system, a visual analysis tool for the visualisation and analysis of large and complex networks. GEOMI provides a collection of network analysis methods, graph lay- out algorithms and several graph navigation and interaction methods. GEOMI is part of a new generation of visual analysis tools combining graph visualisat...

This report presents the design and implementation of Ant Colony Optimisation (ACO) based heuristic for solving the Layer Assignment Problem (LAP) for a directed acyclic graph (DAG). This heuristic produces compact layerings by trying to minimise their width and height. It takes into account the contribution of dummy vertices to the width of the re...

We propose two fast heuristics for solving the NP-hard problem of graph layering with the minimum width and consideration of dummy nodes. Our heuristics can be used at the layer-assignment phase of the Sugiyama method for drawing of directed graphs. We evaluate our heuristics by comparing them to the widely used fast-layering algorithms in an exten...

We introduce a new graph drawing convention for 3D layered drawings of directed graphs. The vertex set is partitioned into layers with all edges pointing in the same direction. The layers occupy parallel planes and vertices in each layer occupy two parallel lines. Thus, the traditional 2D layered drawing of a directed graph is split into two vertic...

Cluttered drawings of graphs cannot efiectively con- vey the information of graphs. Two issues might cause node overlapping when one draws a picture of a graph. The flrst issue occurs when applying a layout algorithm for an abstract graph to a practical appli- cation in which nodes are labeled. The second is the changing of a node's size in a dynam...

We propose a new graph layering heuristic which can be used for hierarchical graph drawing with the minimum width. Our heuristic takes into account the space occupied by both the nodes and the edges of a directed acyclic graph and constructs layerings which are narrower that layerings constructed by the known layering algorithms. It can be used as...

We present a work in progress describing attribute grammar approaches to Grammatical Evolution, which allow us to encode context-sensitive and semantic information. Performance of the different grammars adopted are directly compared with a more traditional GA representation on five instances of an NP-hard knapsack problem. The results presented are...