Abstract Nowadays users leave numerous comments on different social networks, news portals, and forums. Some of the comments are toxic or abusive. Due to numbers of comments, it is unfeasible to manually moderate them, so most of the systems use some kind of automatic discovery of toxicity using machine learning models. In this work, we performed a systematic review of the state-of-the-art in toxic comment classification using machine learning methods. We extracted data from 31 selected primary relevant studies. First, we have investigated when and where the papers were published and their maturity level. In our analysis of every primary study we investigated: data set used, evaluation metric, used machine learning methods, classes of toxicity, and comment language. We finish our work with comprehensive list of gaps in current research and suggestions for future research themes related to online toxic comment classification problem.
{"title":"Machine learning methods for toxic comment classification: a systematic review","authors":"Darko Androcec","doi":"10.2478/ausi-2020-0012","DOIUrl":"https://doi.org/10.2478/ausi-2020-0012","url":null,"abstract":"Abstract Nowadays users leave numerous comments on different social networks, news portals, and forums. Some of the comments are toxic or abusive. Due to numbers of comments, it is unfeasible to manually moderate them, so most of the systems use some kind of automatic discovery of toxicity using machine learning models. In this work, we performed a systematic review of the state-of-the-art in toxic comment classification using machine learning methods. We extracted data from 31 selected primary relevant studies. First, we have investigated when and where the papers were published and their maturity level. In our analysis of every primary study we investigated: data set used, evaluation metric, used machine learning methods, classes of toxicity, and comment language. We finish our work with comprehensive list of gaps in current research and suggestions for future research themes related to online toxic comment classification problem.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"143 1","pages":"205 - 216"},"PeriodicalIF":0.3,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89979556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This paper initiates a study on a new coloring regime which sets conditions in respect of the degrees deg(v) and deg(u) where, v, u ∈ V(G) and vu ∈ E(G). This new coloring regime is called, ”degree tolerant coloring”. The degree tolerant chromatic number is defined. A number of interesting introductory results are presented. Amongst others, new Nordhaus-Gaddum type bounds are provided.
{"title":"Degree tolerant coloring of graph","authors":"J. Kok","doi":"10.2478/ausi-2020-0013","DOIUrl":"https://doi.org/10.2478/ausi-2020-0013","url":null,"abstract":"Abstract This paper initiates a study on a new coloring regime which sets conditions in respect of the degrees deg(v) and deg(u) where, v, u ∈ V(G) and vu ∈ E(G). This new coloring regime is called, ”degree tolerant coloring”. The degree tolerant chromatic number is defined. A number of interesting introductory results are presented. Amongst others, new Nordhaus-Gaddum type bounds are provided.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"10 1","pages":"217 - 231"},"PeriodicalIF":0.3,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77264970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In this paper we will be taking a look at type inference and its uses for binding-time analysis, dynamic typing and better error messages. We will propose a new binding-time analysis algorithm ℬ, which is a modification of an already existing algorithm by Gomard [4], and discuss the speed difference.
{"title":"Enhanced type inference for binding-time analysis","authors":"Mátyás Szokoli, A. Kiss","doi":"10.2478/ausi-2020-0014","DOIUrl":"https://doi.org/10.2478/ausi-2020-0014","url":null,"abstract":"Abstract In this paper we will be taking a look at type inference and its uses for binding-time analysis, dynamic typing and better error messages. We will propose a new binding-time analysis algorithm ℬ, which is a modification of an already existing algorithm by Gomard [4], and discuss the speed difference.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"16 1","pages":"232 - 250"},"PeriodicalIF":0.3,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75305535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The Multiplayer Online Battle Arena (MOBA) game is a popular type for its competition between players. Due to the high complexity, balance is the most important factor to secure a fair competitive environment. The common way to achieve dynamic data balance is by constant updates. The traditional method of finding unbalanced factors is mostly based on professional tournaments, a small minority of all the games and not real time. We develop an evaluation system for the DOTA2 based on big data with clustering analysis, neural networks, and a small-scale data collection as a sample. We then provide an ideal matching system based on the Elo rating system and an evaluation system to encourage players to try more different heroes for a diversified game environment and more data supply, which makes for a virtuous circle in the evaluation system.
{"title":"Improved balance in multiplayer online battle arena games","authors":"Chailong Huang, S. Bruda","doi":"10.2478/ausi-2020-0011","DOIUrl":"https://doi.org/10.2478/ausi-2020-0011","url":null,"abstract":"Abstract The Multiplayer Online Battle Arena (MOBA) game is a popular type for its competition between players. Due to the high complexity, balance is the most important factor to secure a fair competitive environment. The common way to achieve dynamic data balance is by constant updates. The traditional method of finding unbalanced factors is mostly based on professional tournaments, a small minority of all the games and not real time. We develop an evaluation system for the DOTA2 based on big data with clustering analysis, neural networks, and a small-scale data collection as a sample. We then provide an ideal matching system based on the Elo rating system and an evaluation system to encourage players to try more different heroes for a diversified game environment and more data supply, which makes for a virtuous circle in the evaluation system.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"7 1","pages":"183 - 204"},"PeriodicalIF":0.3,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81001424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The paper presents some of our recent results in the field of computer emulation for supporting and enhancing the educational processes. The ATmega 328P micro-controller emulator has been developed as a set of emuStudio emulation platform extension modules (plug-ins). The platform is used at the Department of Computers and Informatics as a studying and teaching support tool. Within the Assembler course, currently, the Intel 8080 architecture and language is briefly described as a preliminary preparation material for the study of Intel x86 architecture, and the Intel 8080 emuStudio emulator module is used here. The aim of this work is to explore the possibility to enrich the course by introducing a more up-to-date and relevant technology and the ATmega is the heart of Arduino – a popular hardware and software prototyping platform. We consider the options to make the process of studying the assembly language principles more attractive for students and using the ATmega AVR architecture, which is broadly deployed in embedded systems, seems to be one of them.
{"title":"Development of ATmega 328P micro-controller emulator for educational purposes","authors":"Michael J. Sipos, Slavomír Simonák","doi":"10.2478/ausi-2020-0010","DOIUrl":"https://doi.org/10.2478/ausi-2020-0010","url":null,"abstract":"Abstract The paper presents some of our recent results in the field of computer emulation for supporting and enhancing the educational processes. The ATmega 328P micro-controller emulator has been developed as a set of emuStudio emulation platform extension modules (plug-ins). The platform is used at the Department of Computers and Informatics as a studying and teaching support tool. Within the Assembler course, currently, the Intel 8080 architecture and language is briefly described as a preliminary preparation material for the study of Intel x86 architecture, and the Intel 8080 emuStudio emulator module is used here. The aim of this work is to explore the possibility to enrich the course by introducing a more up-to-date and relevant technology and the ATmega is the heart of Arduino – a popular hardware and software prototyping platform. We consider the options to make the process of studying the assembly language principles more attractive for students and using the ATmega AVR architecture, which is broadly deployed in embedded systems, seems to be one of them.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"102 1","pages":"159 - 182"},"PeriodicalIF":0.3,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78746699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Suppressed fuzzy c-means clustering was proposed as an attempt to combine the better properties of hard and fuzzy c-means clustering, namely the quicker convergence of the former and the finer partition quality of the latter. In the meantime, it became much more than that. Its competitive behavior was revealed, based on which it received two generalization schemes. It was found a close relative of the so-called fuzzy c-means algorithm with generalized improved partition, which could improve its popularity due to the existence of an objective function it optimizes. Using certain suppression rules, it was found more accurate and efficient than the conventional fuzzy c-means in several, mostly image processing applications. This paper reviews the most relevant extensions and generalizations added to the theory of fuzzy c-means clustering models with suppressed partitions, and summarizes the practical advances these algorithms can offer.
{"title":"A review on suppressed fuzzy c-means clustering models","authors":"L. Szilágyi, László Lefkovits, David Iclanzan","doi":"10.2478/ausi-2020-0018","DOIUrl":"https://doi.org/10.2478/ausi-2020-0018","url":null,"abstract":"Abstract Suppressed fuzzy c-means clustering was proposed as an attempt to combine the better properties of hard and fuzzy c-means clustering, namely the quicker convergence of the former and the finer partition quality of the latter. In the meantime, it became much more than that. Its competitive behavior was revealed, based on which it received two generalization schemes. It was found a close relative of the so-called fuzzy c-means algorithm with generalized improved partition, which could improve its popularity due to the existence of an objective function it optimizes. Using certain suppression rules, it was found more accurate and efficient than the conventional fuzzy c-means in several, mostly image processing applications. This paper reviews the most relevant extensions and generalizations added to the theory of fuzzy c-means clustering models with suppressed partitions, and summarizes the practical advances these algorithms can offer.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"46 1","pages":"302 - 324"},"PeriodicalIF":0.3,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85464376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The concept of the statistical complexity is studied to characterize the classical kicked top model which plays important role in the qbit systems and the chaotic properties of the entanglement. This allow us to understand this driven dynamical system by the probability distribution in phase space to make distinguish among the regular, random and structural complexity on finite simulation. We present the dependence of the kicked top and kicked rotor model through the strength excitation in the framework of statistical complexity.
{"title":"Statistical complexity of the kicked top model considering chaos","authors":"Á. Fülöp","doi":"10.2478/ausi-2020-0017","DOIUrl":"https://doi.org/10.2478/ausi-2020-0017","url":null,"abstract":"Abstract The concept of the statistical complexity is studied to characterize the classical kicked top model which plays important role in the qbit systems and the chaotic properties of the entanglement. This allow us to understand this driven dynamical system by the probability distribution in phase space to make distinguish among the regular, random and structural complexity on finite simulation. We present the dependence of the kicked top and kicked rotor model through the strength excitation in the framework of statistical complexity.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"25 1","pages":"283 - 301"},"PeriodicalIF":0.3,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88002720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Formal concept analysis (FCA) is a method based on lattice theory, widely used for data visualization, data analysis and knowledge discovery. Amino acids (AAs) are chemical molecules that constitute the proteins. In this paper is presented a new and easy way of visualizing of the structure and properties of AAs. In addition, we performed a new Hydrophobic-Polar classification of AAs using FCA. For this, the 20 proteinogenic AAs were clustered, classified by hydrophobicity and visualized in Hasse-diagrams. Exploring and processing the dataset was done with Elba and ToscanaJ, some FCA tools and Conceptual Information System (CIS).
{"title":"Formal concept analysis for amino acids classification and visualization","authors":"Adrian-Sorin Telcian, D. Cristea, Ioan Sima","doi":"10.2478/ausi-2020-0002","DOIUrl":"https://doi.org/10.2478/ausi-2020-0002","url":null,"abstract":"Abstract Formal concept analysis (FCA) is a method based on lattice theory, widely used for data visualization, data analysis and knowledge discovery. Amino acids (AAs) are chemical molecules that constitute the proteins. In this paper is presented a new and easy way of visualizing of the structure and properties of AAs. In addition, we performed a new Hydrophobic-Polar classification of AAs using FCA. For this, the 20 proteinogenic AAs were clustered, classified by hydrophobicity and visualized in Hasse-diagrams. Exploring and processing the dataset was done with Elba and ToscanaJ, some FCA tools and Conceptual Information System (CIS).","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"42 1","pages":"22 - 38"},"PeriodicalIF":0.3,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84008952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Using software applications or services, which provide word or even word pattern recommendation service has become part of our lives. Those services appear in many form in our daily basis, just think of our smartphones keyboard, or Google search suggestions and this list can be continued. With the help of these tools, we can not only find the suitable word that fits into our sentence, but we can also express ourselves in a much more nuanced, diverse way. To achieve this kind of recommendation service, we use an algorithm which is capable to recommend word by word pattern queries. Word pattern queries, can be expressed as a combination of words, part-of-speech (POS) tags and wild card words. Since there are a lot of possible patterns and sentences, we use Big Data frameworks to handle this large amount of data. In this paper, we compared two popular framework Hadoop and Spark with the proposed algorithm and recommend some enhancement to gain faster word pattern generation.
{"title":"Word pattern prediction using Big Data frameworks","authors":"B. Szabari, A. Kiss","doi":"10.2478/ausi-2020-0004","DOIUrl":"https://doi.org/10.2478/ausi-2020-0004","url":null,"abstract":"Abstract Using software applications or services, which provide word or even word pattern recommendation service has become part of our lives. Those services appear in many form in our daily basis, just think of our smartphones keyboard, or Google search suggestions and this list can be continued. With the help of these tools, we can not only find the suitable word that fits into our sentence, but we can also express ourselves in a much more nuanced, diverse way. To achieve this kind of recommendation service, we use an algorithm which is capable to recommend word by word pattern queries. Word pattern queries, can be expressed as a combination of words, part-of-speech (POS) tags and wild card words. Since there are a lot of possible patterns and sentences, we use Big Data frameworks to handle this large amount of data. In this paper, we compared two popular framework Hadoop and Spark with the proposed algorithm and recommend some enhancement to gain faster word pattern generation.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"24 1","pages":"51 - 69"},"PeriodicalIF":0.3,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78842627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Let R be a commutative ring with Z*(R) as the set of non-zero zero divisors. The zero divisor graph of R, denoted by Γ(R), is the graph whose vertex set is Z*(R), where two distinct vertices x and y are adjacent if and only if xy = 0. In this paper, we investigate the metric dimension dim(Γ(R)) and upper dimension dim+(Γ(R)) of zero divisor graphs of commutative rings. For zero divisor graphs Γ(R) associated to finite commutative rings R with unity 1 ≠ 0, we conjecture that dim+(Γ(R)) = dim(Γ(R)), with one exception that R≅Π2n {rm{R}} cong Pi {rmmathbb{Z}}_2^{rm{n}} , n ≥ 4. We prove that this conjecture is true for several classes of rings. We also provide combinatorial formulae for computing the metric and upper dimension of zero divisor graphs of certain classes of commutative rings besides giving bounds for the upper dimension of zero divisor graphs of rings.
{"title":"Metric and upper dimension of zero divisor graphs associated to commutative rings","authors":"S. Pirzada, M. Aijaz","doi":"10.2478/ausi-2020-0006","DOIUrl":"https://doi.org/10.2478/ausi-2020-0006","url":null,"abstract":"Abstract Let R be a commutative ring with Z*(R) as the set of non-zero zero divisors. The zero divisor graph of R, denoted by Γ(R), is the graph whose vertex set is Z*(R), where two distinct vertices x and y are adjacent if and only if xy = 0. In this paper, we investigate the metric dimension dim(Γ(R)) and upper dimension dim+(Γ(R)) of zero divisor graphs of commutative rings. For zero divisor graphs Γ(R) associated to finite commutative rings R with unity 1 ≠ 0, we conjecture that dim+(Γ(R)) = dim(Γ(R)), with one exception that R≅Π2n {rm{R}} cong Pi {rmmathbb{Z}}_2^{rm{n}} , n ≥ 4. We prove that this conjecture is true for several classes of rings. We also provide combinatorial formulae for computing the metric and upper dimension of zero divisor graphs of certain classes of commutative rings besides giving bounds for the upper dimension of zero divisor graphs of rings.","PeriodicalId":41480,"journal":{"name":"Acta Universitatis Sapientiae Informatica","volume":"23 1","pages":"101 - 84"},"PeriodicalIF":0.3,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75200131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：