Computer Science Research Research Articles

Twitter spam and false accounts prevalence, detection, and characterization: A survey

The issue of quantifying and characterizing various forms of social media manipulation and abuse has been at the forefront of the computational social science research community for over a decade. In this paper, I provide a (non-comprehensive) survey of research efforts aimed at estimating the prevalence of spam and false accounts on Twitter, as well as characterizing their use, activity, and behavior. I propose a taxonomy of spam and false accounts, enumerating known techniques used to create and detect them. Then, I summarize studies estimating the prevalence of spam and false accounts on Twitter. Finally, I report on research that illustrates how spam and false accounts are used for scams and frauds, stock market manipulation, political disinformation and deception, conspiracy amplification, coordinated influence, public health misinformation campaigns, radical propaganda and recruitment, and more. I will conclude with a set of recommendations aimed at charting the path forward to combat these problems.

A model-based approach for specifying changes in replications of empirical studies in computer Science

The need of replicating empirical studies in Computer Science is widely recognized among the research community. It is essential to report the changes of each replication to promote not only the comprehensibility of the evolution of the experimental validity across a family of studies, but also replicability itself. Unfortunately, the lack of proposals for systematic reporting of changes in replications undermines these desirable objectives. The main goal of the work presented in this article is to provide researchers in Computer Science with a systematic tool-supported approach for the specification and reporting of changes in the replications of their empirical studies. Applying Design Science Research, we have developed and validated a composite artifact consisting of (i) a metamodel that formalizes all the relevant concepts related to replications and their changes; (ii) templates and linguistic patterns that facilitate their reporting; and (iii) a proof-of-concept model-based software tool that supports the proposed approach. For its validation, we have carried out a multiple case study that includes 9 families of empirical studies not only from Computer Science, but also from an area as different as Agrobiology , to check the external validity of our approach. The 9 families encompass 23 replication studies and a total of 92 replication changes, for which we have analyzed the suitability of our proposal. The multiple case study revealed some initial limitations of our approach related to threats to experimental validity and context variables. After several improvement iterations on the artifact, all of the 92 replication changes could be properly specified, including also their qualitatively estimated effects on experimental validity and their corresponding visualization. Our proposal for the specification of replication changes seems to fit the needs not only of replications in Computer Science, but also in other research areas. Nevertheless, further research is needed to improve it and disseminate its use among the research community.

Guest Editorial: Learning, optimisation and control of cyber‐physical systems

Guest Editorial: Learning, optimisation and control of cyber‐physical systems

A Bibliometric Overview of the IEEE Transactions on Learning Technologies

<sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IEEE Transactions on Learning Technologies</small> (IEEE-TLT) is a leading journal in the fields of computer science and educational research with a focus on learning technologies. It published its first issue in 2008 and commemorated its 15th anniversary in 2022. Inspired by this event, this article provides a general lifetime overview of the journal using bibliometric indicators and science mapping analysis. The main objective is to provide a complete overview of the main components that have affected the journal. This analysis includes key factors such as the most cited articles and the leading authors, institutions, and countries for the journal, along with an insight into the publication and the citation structure. We use the Web of Science Core Collection database to analyze the bibliometric data and VOSviewer software to graphically map the bibliographic material using a bibliographic coupling, cocitation, and co-occurrence of author keywords. With this analysis, we gain a deeper understanding of how IEEE-TLT is connected to other journals and researchers across the globe and how it contributes to scientific communities. Results indicate that IEEE-TLT is a high-impact journal in computer Science and education and has been referenced by a wide range of authors, institutions, countries, and the main topics related to learning technologies from all over the world.

Energy-Efficiency versus Carbon-Efficiency

Improving the energy-efficiency of computing systems has been the focus of computer science research for many decades. In the data center domain, for example, there has been an intense focus on improving energy efficiency by improving the Power Usage Effectiveness (PUE) of data centers. Other domains such as civil and mechanical engineering have also focused on improving the energy efficiency of built environments such as buildings. More recently, there has been an increased emphasis on sustainability on the human-built infrastructure of various kinds motivated by climate change, which has resulted in an emphasis on reducing carbon emissions of such infrastructure by optimizing their carbon efficiency.

Combinatorial Optimization

Combinatorial Optimization deals with optimization problems defined on combinatorial structures such as graphs and networks. Motivated by diverse practical problem setups, the topic has developed into a rich mathematical discipline with many connections to other fields of Mathematics (such as, e.g., Combinatorics, Convex Optimization and Geometry, and Real Algebraic Geometry). It also has strong ties to Theoretical Computer Science and Operations Research. A series of Oberwolfach Workshops have been crucial for establishing and developing the field. The workshop we report about was a particularly exciting event—due to the depth of results that were presented, the spectrum of developments that became apparent from the talks, the breadth of the connections to other mathematical fields that were explored, and last but not least because for many of the particiants it was the first opportunity to exchange ideas and to collaborate during an on-site workshop since almost two years.

Optimal decisions in stochastic graphs with uncorrelated and correlated edge weights

Stochastic graph models and algorithms for the computation of different stochastic shortest path problems (SSPPs) continue to play an important role in various fields of computer science and operations research, with recent applications ranging from vehicle routing to social networks and decision problems in finance. In this paper, we first introduce stochastic graph models where weights to pass an edge in a graph are, possibly correlated, random variables. Depending on the application context and the interpretation of uncertain edge weights, random variables either model the time to pass an edge or describe a reward one gains by traversing an edge. For modeling the random variables discrete phase type distributions are used. Several algorithms for the computation of optimal policies which depend on the current weight upon arriving at a vertex while still exploiting weight dependencies among edges are developed. It will be shown that with correlated edge weights the stochastic shortest path problems become PSPACE-complete and the solution of instances with a bounded number of phases is NP-hard such that for an exact computation of the shortest path, algorithms from partially observable Markov decision processes (POMDPs) or mixed integer linear programming (MILP) have to be applied. Alternatively, an efficient heuristic algorithm can be used which often yields good or even optimal results with a small effort.

Research topic flows in co-authorship networks

AbstractIn scientometrics, scientific collaboration is often analyzed by means of co-authorships. An aspect which is often overlooked and more difficult to quantify is the flow of expertise between authors from different research topics, which is an important part of scientific progress. With the Topic Flow Network (TFN) we propose a graph structure for the analysis of research topic flows between scientific authors and their respective research fields. Based on a multi-graph and a topic model, our proposed network structure accounts for intratopic as well as intertopic flows. Our method requires for the construction of a TFN solely a corpus of publications (i.e., author and abstract information). From this, research topics are discovered automatically through non-negative matrix factorization. The thereof derived TFN allows for the application of social network analysis techniques, such as common metrics and community detection. Most importantly, it allows for the analysis of intertopic flows on a large, macroscopic scale, i.e., between research topic, as well as on a microscopic scale, i.e., between certain sets of authors. We demonstrate the utility of TFNs by applying our method to two comprehensive corpora of altogether 20 Mio. publications spanning more than 60 years of research in the fields computer science and mathematics. Our results give evidence that Topic Flow Networks are suitable, e.g., for the analysis of topical communities, the discovery of important authors in different fields, and, most notably, the analysis of intertopic flows, i.e., the transfer of topical expertise. Besides that, our method opens new directions for future research, such as the investigation of influence relationships between research fields.

Collaboration Trend and its Impact on the Research Productivity in Computer Science Research

Apart from a few bibliometric studies of limited scope, the Pakistani scientific system is a scantly researched area requiring large-scale empirical evidence-based studies. This study aims to explore various features of collaboration in research and its impact on the performance of computer scientists in Pakistan. Over 15,494 SCOPUS-indexed publications in the area of computer science for the period 1997 to 2017, having at least one Pakistani author, were analyzed. The findings of the study disclosed the important role of collaboration in the citation count of the publications. International collaborative works and the more countries in collaboration significantly impacted the number of citations. The study's findings revealed that collaborative publications are more frequently cited and considered of high quality. This study is the first large-scale quantitative analysis of research collaboration, represented by co-authorship in computer science research in Pakistan.

SYSTEM-INFORMATION MODELS FOR INTELLIGENT INFORMATION PROCESSING

The subject of the study is system-information models of processes and systems and their use for intelligent processing of information in production tasks. The use of intelligent information processing in production management systems is currently one of the key areas of development of informatics. The aim of the work is to develop system-information models of processes and systems for intelligent information processing allowing to analyze and solve production problems, in conditions of uncertainty. In the article the following tasks are solved: to analyze approaches to the definition of information characteristics of processes and systems; to develop the basis for modeling of system-information processes and systems for intelligent information processing; to develop system-information models and ways of their application for intelligent information processing in the tasks of production. The following methods are used: system-information approach to processes and systems; system-information modeling of processes and systems. The following results were obtained: the analysis of approaches to the definition of information characteristics of processes and systems; developed principles of modeling system-information processes and systems for intelligent processing of information; introduced the concepts of system information and information measure; developed system-information models and methods of their application for the intelligent processing of information in the tasks of production. Conclusions. The development of methods for solving various classes of practical problems using intelligent information processing is one of the key areas of research in computer science. The developed system-information models of processes and systems for intelligent information processing allow analyzing and solving problems. Thereby increase the efficiency of solving problems of analysis, synthesis and forecasting of production systems and technologies, as well as problems of production management. The system-information approach to processes and systems operates with new concepts – system information and information measure, it allowed developing system-information models for intelligent processing of information, as well as ways of their application at stages of product life cycle, which allowed solving problems of production. System-information models of processes and systems describe interaction between source and receiver on information level on the basis of sensitivity threshold. The communication channel between the source and the receiver of information operates, as a rule, under conditions of uncertainty, which can lead to the loss of information during transmission due to possible changes in the characteristics of the system. To describe their interaction, some models of intelligent information processing can be used, in particular, neural network models or fuzzy inference models. Their use will improve the efficiency of receiver state prediction, taking into account the state of the transmitter and the conditions of communication channel operation. The presented article has shown the relevance of developing system-information models for intelligent information processing at the levels of data reception, interpretation and communication, which allows expanding the class of solved production tasks.

Convolutional Neural Networks-Based Framework for Early Identification of Dementia Using MRI of Brain Asymmetry.

Computer-aided diagnosis of health problems and pathological conditions has become a substantial part of medical, biomedical, and computer science research. This paper focuses on the diagnosis of early and progressive dementia, building on the potential of deep learning (DL) models. The proposed computational framework exploits a magnetic resonance imaging (MRI) brain asymmetry biomarker, which has been associated with early dementia, and employs DL architectures for MRI image classification. Identification of early dementia is accomplished by an eight-layered convolutional neural network (CNN) as well as transfer learning of pretrained CNNs from ImageNet. Different instantiations of the proposed CNN architecture are tested. These are equipped with Softmax, support vector machine (SVM), linear discriminant (LD), or [Formula: see text] -nearest neighbor (KNN) classification layers, assembled as a separate classification module, which are attached to the core CNN architecture. The initial imaging data were obtained from the MRI directory of the Alzheimer's disease neuroimaging initiative 3 (ADNI3) database. The independent testing dataset was created using image preprocessing and segmentation algorithms applied to unseen patients' imaging data. The proposed approach demonstrates a 90.12% accuracy in distinguishing patients who are cognitively normal subjects from those who have Alzheimer's disease (AD), and an 86.40% accuracy in detecting early mild cognitive impairment (EMCI).

(Retracted) Modeling of human action recognition using hyperparameter tuned deep learning model

Recently, human action recognition (HAR) has become an important focus of computer science research because of its applications in surveillance, robotics, sentiment analysis, and other areas. Human activity classification is a time-consuming operation, especially when photos are cluttered, and the background is unclear. In addition, conventional machine learning models fail to achieve robust performance due to the increasing number of activities. Comparatively, deep learning (DL) approaches help to automatically learn and describe the necessary features of the input data with low manual work and robust discriminant abilities. In addition, a preprocessing stage is included in this study’s HAR utilizing hyperparameter tuned DL (HAR-HPTDL) model that removes undesired background and improves the quality of the input. The model also implements a bidirectional long short-term memory model as a feature extractor, the sparrow search algorithm to tune the hyperparameters, and a SoftMax layer for the effective classification of human actions. In addition, the curse of dimensionality can be overcome via entropy-based feature reduction and Chi square-based feature selection. Based on a variety of measures, the HAR-HPTDL methodology has been put through its paces with other published techniques. The results indicate that the HAR-HPTDL technique outperforms current state-of-the-art techniques in simulations. The outcome of this work demonstrates that an HAR-HPTDL model may achieve comparable or even superior recognition accuracy of 0.949 than the prior best deep classifier(s) on all databases with proper parameter optimization.

Functional harmony ontology: Musical harmony analysis with Description Logics

Symbolic representations of music are emerging as an important data domain both for the music industry and for computer science research, aiding in the organization of large collections of music and facilitating the development of creative and interactive AI. An aspect of symbolic representations of music, which differentiates them from audio representations, is their suitability to be linked with notions from music theory that have been developed over the centuries. One core such notion is that of functional harmony, which involves analyzing progressions of chords. This paper proposes a description of the theory of functional harmony within the OWL 2 RL profile and experimentally demonstrates its practical use.

Prediction and Classification of Stress in Humans

To avoid serious health problems, researchers are working difficult to come up with effective methods for detecting and coping with excessive amounts of stress. Facial gestures are an essential part of human speech. Researchers in psychology, computer science, neuroscience, and other fields are increasingly interested in a human-computer interface device for automated face recognition or facial expression recognition. as well as similar areas. The machine identifies frontal faces in photographs and codes each frame according to a series of dimensions. A system for acquiring the corresponding information is inside this case of sentiment classification utilizing a biologic output or a thermodynamic picture, which was being used, it is necessarily researched extensively. To develop efficient strategies for identifying and controlling elevated levels of stress in order to reduce severe health effects. Facial gestures are an essential part of human speech. Researchers are particularly involved in a human-computer interface device for automated face recognition or facial expression recognition. In the photographs, the machine senses frontal facesand codes each frame according to certain dimensions. Experimentation indicate that the proposed algorithm can detect more efficient action

What Has Artifact Evaluation Ever Done for Us?

Artifact evaluation is an established peer review practice in several fields of computer science research. In the security field it only has been introduced recently. The author highlights several benefits of artifact sharing for and beyond the research community, inspects the specifics of the security field, and derives suggestions to foster artifact sharing in the security field. Embracing artifact sharing will help to strengthen and mature the field.

A Bibliometric Analysis: Computer Science Research From Indonesia

Bibliometric indicators originally counted ways to measure research quality. This endured for decades following the term's introduction. The purpose of this research is to carry out a bibliometric analysis of the present status and trends in computer science articles written by Indonesian authors that are included in the Scopus database. Bibliographic indicators were analyzed using SciVal (www.scival.com). Elsevier constructed SciVal using Collexis' semantic technology after buying it in 2010. SciVal evaluates scientific performance using Scopus and tracks funding. Between the years 1998 and 2022, the total number of indexed papers in Scopus that discuss the advancement of research outcomes in computer science has greatly expanded. This rise reached its highest point in 2019, with 121 publications. Santoso is the most prolific Indonesian researcher when it comes to releasing research results on computer science in Indonesia. The University of Indonesia has been the most helpful sponsor in terms of sponsoring computer science research.

Selecting a set of semantic labels to eliminate ambiguity for Vietnamese

The rapid development of automatic control systems in natural language, automatic translation systems based on semantic statistics have been receiving much attention from computer science researchers. However, this method requires a large bilingual corpus and accurate semantic tagging, the construction of which requires a lot of time and effort, because of the ambiguity of the natural language. For Vietnamese, automatic question-and-answer systems are increasingly developing in Vietnam, but the problem of semantic ambiguity has not yet received much attention from domestic studies. In this paper, we build a model to evaluate and select an effective and reasonable set of semantic labels from 3 commonly used sets of semantic labels: LLOCE (Longman Lexicon of Contemporary English), LDOCE (Longman Dictionary) of Contemporary English) and WordNet. And then, select the appropriate set of labels, apply it to automatic semantic labeling systems for Vietnamese, help eliminate semantic ambiguity, and support automatic translation, automatic question-and-answer systems efficiently.

Contribution of Synthetic Data Generation towards an Improved Patient Stratification in Palliative Care.

AI model development for synthetic data generation to improve Machine Learning (ML) methodologies is an integral part of research in Computer Science and is currently being transferred to related medical fields, such as Systems Medicine and Medical Informatics. In general, the idea of personalized decision-making support based on patient data has driven the motivation of researchers in the medical domain for more than a decade, but the overall sparsity and scarcity of data are still major limitations. This is in contrast to currently applied technology that allows us to generate and analyze patient data in diverse forms, such as tabular data on health records, medical images, genomics data, or even audio and video. One solution arising to overcome these data limitations in relation to medical records is the synthetic generation of tabular data based on real world data. Consequently, ML-assisted decision-support can be interpreted more conveniently, using more relevant patient data at hand. At a methodological level, several state-of-the-art ML algorithms generate and derive decisions from such data. However, there remain key issues that hinder a broad practical implementation in real-life clinical settings. In this review, we will give for the first time insights towards current perspectives and potential impacts of using synthetic data generation in palliative care screening because it is a challenging prime example of highly individualized, sparsely available patient information. Taken together, the reader will obtain initial starting points and suitable solutions relevant for generating and using synthetic data for ML-based screenings in palliative care and beyond.

Machine Learning in Electronic and Biomedical Engineering

In recent years, machine learning (ML) algorithms have become of paramount importance in computer science research, both in the electronic and biomedical fields [...]

Training and Development in Times of Automation: A Conceptual Roadmap for HRM

As automation of machines proceeds with high acceleration, human resource management (HRM) is challenged to prepare the organization for a “real” collaboration of humans and machines. In order to develop appropriate coping strategies and control systems for HRM, we design a conceptual roadmap for training and development in times of automation in the near and far future. We equally draw from management and computer science research by combining technical-centered and human-centered approaches for training and development. By conceiving humans and machines as complementary actors in the organizations of the future, we suggest four training directions. Our roadmap emphasizes that a fully integrated management of human and machine resources enables HRM to optimize and evaluate the collaborative development of machines and humans. Our research underlines the importance of combining human resource training and development with the progression of automation.