Maxim Mozgovoy

ORCID: 0000-0003-0684-4012
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Artificial Intelligence in Games
  • Natural Language Processing Techniques
  • Sports Analytics and Performance
  • Topic Modeling
  • Educational Games and Gamification
  • Academic integrity and plagiarism
  • Reinforcement Learning in Robotics
  • Teaching and Learning Programming
  • Software Testing and Debugging Techniques
  • Software Engineering Research
  • Speech and dialogue systems
  • Advanced Malware Detection Techniques
  • Multi-Agent Systems and Negotiation
  • Sentiment Analysis and Opinion Mining
  • Imbalanced Data Classification Techniques
  • Semantic Web and Ontologies
  • Mobile and Web Applications
  • Time Series Analysis and Forecasting
  • Innovative Teaching and Learning Methods
  • Digital Games and Media
  • Educational and Psychological Assessments
  • Online Learning and Analytics
  • Human Pose and Action Recognition
  • EFL/ESL Teaching and Learning
  • AI-based Problem Solving and Planning

University of Aizu
2015-2024

Peter the Great St. Petersburg Polytechnic University
2015

Joensuu Science Park
2005-2006

Learning diaries are instruments through which students can reflect on their learning experience. Students' sentiments, emotions, opinions and attitudes embedded in as part of the process understanding progress during course self-awareness goals. also a very informative feedback source for instructors regarding students' emotional well-being. However number created become daunting task to be manually analyzed with care, particularly when class is large. To tackle this problem, paper we...

10.1145/2526968.2526984 article EN 2013-11-14

Gamification of language learning is a clear trend recent years. Widespread use smartphones and the rise mobile gaming as popular leisure activity contribute to popularity gamification, application developers can rely on an unprecedented reach their products expect acceptance game-like elements by users. In terms content, however, most apps implement traditional activities, such reading, listening, translating, solving quizzes. This article discusses gamification natural grammar with app...

10.1177/0735633119833010 article EN Journal of Educational Computing Research 2019-02-26

The availability and use of computers in teaching has seen an increase the rate plagiarism among students because wide electronic texts online. While computer tools that have appeared recent years are capable detecting simple forms plagiarism, such as copy-paste, a number research studies devoted to evaluation comparison detection revealed these contain limitations complex extensive paraphrasing technical tricks, replacing original characters with similar-looking from foreign alphabets. This...

10.2190/ec.43.4.e article EN Journal of Educational Computing Research 2010-12-01

Plagiarism has become a serious problem in education, and several plagiarism detection systems have been developed for dealing with this problem. This study provides an empirical evaluation of eight student essays. We present categorical hierarchy the most common types that are encountered texts. Our purpose-built test set contains texts which instances commonly utilized plagiaristic techniques embedded. While Sherlock was clearly overall best hermetic system, SafeAssignment performed...

10.2190/ec.42.2.a article EN Journal of Educational Computing Research 2010-02-09

10.1016/j.ipl.2006.06.009 article EN Information Processing Letters 2006-08-03

Plagiarism in universities has always been a difficult problem to overcome. Various tools have developed over the past few years help teachers detect plagiarism students' work. By being able categorize multitude of detection tools, it is possible estimate their capabilities, advantages and disadvantages. In this article I consider modern software solutions, paying attention mostly desktop systems intended for program code. also speed reliability different that are currently available.

10.15388/infedu.2006.08 article EN cc-by Informatics in Education 2006-04-15

Spatiotemporal datasets based on player tracking are widely used in sports analytics research. Common research tasks often require the analysis of game events, such as passes, fouls, tackles, and shots goal. However, spatiotemporal usually do not include event information, which means it has to be reconstructed automatically. We propose a rule-based algorithm for identifying several basic types events soccer, including ball possession, successful unsuccessful Our aim is provide simple...

10.3390/app10228046 article EN cc-by Applied Sciences 2020-11-13

The problem of plagiarism detection system design is a subject numerous works the last decades.Various advanced file-file comparison techniques were developed.However, most existing systems, aimed at natural language texts, do not perform any significant preprocessing input documents.So in many cases it possible to hide presence by utilizing some simple techniques.In this work we show how parser can be used fight against basic hiding methods.

10.21437/slate.2007-22 article EN 2007-10-01

The rapid development of complex virtual worlds (most notably, in 3D computer and video games) introduces new challenges for the creation agents, controlled by artificial intelligence (AI) systems. Two important subproblems this topic area which need to be addressed are (a) believability (b) effectiveness agents’ behavior, i.e., human-likeness characters high ability achieving their own goals. In paper, authors study current approaches AI behavior worlds. They examine concepts effectiveness,...

10.4018/jgcms.2012040103 article EN International Journal of Gaming and Computer-Mediated Simulations 2012-04-01

Sport games are among the oldest and best established genres of computer games. Sport-inspired environments, such as RoboCup, have been used for AI benchmarking years. We argue that, in spite rise increasingly more sophisticated game genres, team sport will remain an important testbed due to two primary factors. First, there several genre-specific challenges systems that neither present nor emphasized other types games, frequent replanning. Second, unmistakable nonskill-related goals...

10.1155/2021/5521877 article EN cc-by International Journal of Computer Games Technology 2021-05-30

Abstract This paper explains design decisions forming a foundation of WordBricks — an intelligent computer-assisted language learning environment, recently initiated at our institution. is intended to serve as “virtual lab” that supports open experiments with natural constructions. Being based on dependency grammars, this instrument illustrates the use modern processing technologies in learning. The latest prototypes also show how dependency-styled constructions can be represented more...

10.1186/2192-1962-3-5 article EN cc-by Human-centric Computing and Information Sciences 2013-04-08

Plagiarism and similarity detection software is well-known in universities for years. Despite the variety of methods approaches used plagiarism detection, typical trade-off between speed reliability algorithm still remains. We introduce a new two-step approach to that combines high algorithmic performance quality pairwise file comparison. Our system uses fast method select suspicious files only, then invokes precise (and slower) algorithms get reliable results. show proposed does not...

10.1109/fie.2007.4417860 article EN 2007-10-01

We describe a method used to build practical AI system for mobile game of tennis. The chosen approach had support two goals: (1) provide large number believable and diverse characters, (2) let the users train "ghost" characters able substitute them. achieve these goals by learning agents from collected behavior data human-controlled characters. acquired knowledge is case-based reasoning algorithm perform human-like decision making. Our experiments show that resulting indeed exhibit variety...

10.1109/cig.2016.7860420 article EN 2016-09-01

We analyze data collected during the series of experiments aimed at elucidation basic properties human perception, namely, limited capacity ordering events, actions, etc. according to their preference. Previously it was shown that in a wide class human-controlled systems small deviations from equilibrium position do not cause any actions system's operator, so point certain neighborhood is treated as an one. This phenomenon can be described by notion dynamical traps introduced denote region...

10.1145/2160749.2160783 article EN 2012-03-08

The rise of big data has resulted in the proliferation numerous heterogeneous stores. Even though multiple models are used for integrating these data, combining such huge amounts into a single model remains challenging. There is need database management archives to manage volumes without any particular structure which comes from unconnected and unrelated sources. These growing size thus demand special attention. speed with as well varied types involved stored scientific posing further...

10.3390/app12126202 article EN cc-by Applied Sciences 2022-06-18

Abstract English L2 email is an important mode of communication for Japanese university learners. However, learners often find it challenging to vary register in a pragmatically-appropriate manner when emailing. Identifying specific aspects writing that can provide the basis addressing learner needs. A corpus approach help, systematically identifying instances perceived divergence from register-specific norms dataset. Few corpora, however, have focused on appropriate variation English. This...

10.1075/rs.20016.nic article EN Register Studies 2022-10-18
Coming Soon ...