Abstract Background: Learning Management Systems (LMS) represent one of the main technology to support learning in HE institutions. However, every educational institution differs its experience with usage these systems. South East European University’s LMS is longer than a decade. From last year SEE – University adopting Google Classroom (GC) as an solution. Objectives: Identifying factors which encourage activities, special emphasis on SEEU, might be crucial importance for Higher Education...

Abstract Background: Text classification is a very important task in information retrieval. Its objective to classify new text documents set of predefined classes, using different supervised algorithms. Objectives: We focus on the for Albanian news articles two approaches. Methods/Approach: In first approach, words collection are considered as independent components, allocating each them conforming vector vector’s space. Here we utilized nine classifiers from scikit-learn package, training...

Digital transformation is the process of consuming digital technologies that drives business improvements and customer experience. Artificial intelligence plays a crucial role in businesses' agendas. Technologies algorithms are an important perspective implementation chatbots. AI chatbots use natural language processing technology offer solutions for modernizing traditional processes. The key advantage different domains impact by improving customers' experience reducing costs. Chatbots...

Authorship classification analyzes an author's prior work to identify their writing style, a unique trait of each language and individual author. This research aims conduct thorough comparative analysis various methods for classifying authorship. The study leverages two corpora: AAALitCorpus Albanian literary texts CCAT10 English columns. We evaluate model-generated features across different configurations. richness the breadth provide significant understanding problem, setting new standard...

Abstract Speech recognition is an interdisciplinary subfield of natural language processing (NLP) that facilitates the and translation spoken into text by machine. plays important role in digital transformation. It widely used different areas such as education, industry, healthcare has recently been many Internet Things Machine Learning applications. The process speech one most difficult processes computer science. Despite numerous searches this domain, optimal method for not yet found. This...

Virtual reality (VR) and augmented (AR) are taking off in almost every part of our living. Lately VR/AR technologies increasingly present education as well. experiences offer a great opportunity to involve motivate students learn through experience. Accordingly, the data research topics publications exploring implementation field also evolving rapidly. To investigate papers trends, this study we used metadata from IEEE database for starting 1990 till 2021. The presents major findings...

Abstract Authorship Analysis (AA) is a natural language processing field that examines the previous works of writers to identify author text based on its features. Studies in authorship analysis include identification, profiling, and verification. Due relevance, many applications this attention has been paid. It widely used attribution historical literature. Other legal linguistics, criminal law, forensic investigations, computer forensics. This paper aims provide an overview work done...

Authorship attribution (AA) is a subfield of NLP that analyzes the author's prior works to determine who wrote text based on its features. Each natural language has characteristics, just like every unique writing style. This study aims conduct an in-depth comparison several AA machine-learning techniques. The specially created Albanian corpus (A3C) and English dataset (Reuters C50) have been used in experiments. Using n-grams, we perform character-level word-level analyses represent We use...

Abstract Background and purpose This study aims to provide a practical perspective on how data mining techniques are used in the home appliance after-sales services. Study investigates can recommendation system help customer service company that plans use improve decision making during its digital transformation process. In addition, provides detailed outline process for developing analyzing platforms analytics such companies. Methodology Case approach is evaluating usability of systems...

Automatic authorship identification is a challenging task that has been the focus of extensive research in natural language processing. Regardless progress made attributing authorship, need for corpora under-resourced languages impedes advancing and examining present methods. To address this gap, we investigate problem attribution Albanian. We introduce newly compiled corpus Albanian newsroom columns literary works analyze machine-learning methods detecting authorship. create set...

Modeling co-authorship networks merely in FOAF, as is common with social networks, suffers the inability to capture semantics which are specific collaboration schemes scientific community. For instance, weight of co-author relation expresses magnitude that between two co-authors subject change dynamically new publications assigned graph. They require mechanisms like rules Semantic Web calculate them. We introduce here a framework (1) extending FOAF ontology, and (2) implementing SWRL...

This paper presents a research done about model of tagging for Albanian texts, using the NLTK toolkit. The uses cascading three taggers with backoff. We use dictionary around 32000 words, together their correspondent POS tags and set regular expressions rules too. A lemmatize module is implemented in order to convert nouns verbs lemma. text tagged initially unigram tagger based on dictionary. used as baseline tagger. correction made not correct lemmatized creating third lookup will be first second

The self-directed learning industry is gathering more and pace nowadays. One of the most common ways in this model YouTube tutorials, which provide worldwide easy access to knowledge. This paper investigates tutorial trends utilising their publicly available data. research limited tutorials for 11 programming languages, but can be replicated any other field interest. obtained data analysed different categories such as spreading through years, video statistics, localisation, language facts,...

One of the main difficulties in Learning Management Systems (LMS) is how to maintain balance between learning and management. The primary aim LMSs was assist educators manage learning. As a result this way thinking, features such as managing content, roster students, similar, mostly were promoted. time goes by, accent research more student experiences efficacy tools. On other hand some argue that evolving Web 2.0 applications, students can be better served by an LMS alternative, toolbox web...

In this study is explored the changing path of e-Learning discipline since its appearance to nowadays. E-Learning has evolved in different ways sectors therefore it might have implications certain periods time sector. A small number things changed last half century as much way we learn. Consequently, a significant research going on throughout these identifying cases success application e-learning. context, presented paper about analysis evolution papers related e-learning and any form...

Abstract This study explores the integration of music and technology, illustrating their potential to collaboratively push boundaries musical exploration. Despite traditionally being viewed as unrelated, combination these two fields can significantly contribute progress development. uses advanced computational methods build a dataset filled with symbolic sequences that belong specific genre. is shown be highly accurate provides detailed analysis frequencies when examined closely,...

The subject of the research presented in this paper is to build a system that will automatically obtain two-level rules for agentive nouns two languages: English and Macedonian. A set pairs base_word - derived_agentive noun constructed all these string edit sequence built using insert, delete replace operations. Using resulting sequences, minimal acyclic finite state automaton constructed, which has only one start final state. From automaton, phonological are obtained. These extended improve...

This paper reports on the creation of a corpus for Albanian language that is intended training and evaluating Automatic Speech Recognition (ASR) systems. The comprises 100 h audio recordings taken from 200 audiobooks covers wide range topics with rich vocabulary. were transcribed manually, strictly verbatim, listened to carefully several times ensure accuracy. was evaluated using various end-to-end models as well Transformer-based architectures. evaluation conducted both testing sets, Word...

Purpose The purpose of the research presented in this paper is about an algorithm used for speed limit determination, cases when there ambiguity determining correct road data a tracked vehicle. This resolves glitch that happens emitted global positioning system (GPS) are ambiguous regarding roads very near to each other. Furthermore, we give solution other difficulties involving accuracy and lack information navigation maps. Design/methodology/approach Our vehicle tracking parses all GPS...

This paper concerns some analyses related to derived agentive nouns. In the first section of this paper, a modeling description noun lexicon is given. It provides brief overview nouns containing components (verbs, objects, adverbials) and elements (models, categories, functions). The second part gives an number various schemes that illustrate topics such as polysemy, collocation, also relationships among verbs, subjects, objects prepositional verb ends suffixes, prepositions. usefulness...