In this paper, we discuss the implementation and evaluation of a project-based self-direct learning competency-based module on AI literacy. This module was developed for various Bachelor's degree programs from the school of Engineering at the University of Applied Sciences and Arts Northwestern Switzerland. The aim of this course is not only to show how AI can help with writing and programming (learning), but also to get students firstly to reflect on working with AI and introduce them to important current debates, and secondly to teach the basics of large language models and central methods of data science. Students should be made aware to academic work (including finding and evaluating sources) with and about AI. During the course, they have to combine analytical and technical skills like programming and web scraping when developing a selfchosen project. An important finding of our work is that, despite their daily engagement with computer science and digital tools, without such specific formats, students are unlikely to acquire the necessary knowledge and critical thinking to navigate the rapidly changing landscape of AI autonomously and confidently.

We discuss in this paper the implementation of a project-based self-direct learning competency-based project module in our Bachelor Data Science programme. The goal of the course is to integrate in a later stage all project modules, which are now divided in two: one with and one without external industry partners, treating different aspects of data science with a pre-defined goal and clear objectives for the project. Switching for a competency-based learner-based paradigm with agile aspects and intrinsic focus, we define the core project goals as secondary and develop core data science competences which are acquired by the students and reflected in a learning journal.

Transliteration is the process of expressing a proper name from a source language in the characters of a target language (e.g. from Cyrillic to Latin characters). We present TRANSLIT, a large-scale corpus with approx. 1.6 million entries in more than 180 languages with about 3 million variations of person and geolocation names. The corpus is based on various public data sources, which have been transformed into a unified format to simplify their usage, plus a newly compiled dataset from Wikipedia. In addition, we apply several machine learning methods to establish baselines for automatically detecting transliterated names in various languages. Our best systems achieve an accuracy of 92% on identification of transliterated pairs.

In this paper, we present CEASR, a Corpus for Evaluating the quality of Automatic Speech Recognition (ASR). It is a data set based on public speech corpora, containing metadata along with transcripts generated by several modern state-of-the-art ASR systems. CEASR provides this data in a unified structure, consistent across all corpora and systems, with normalised transcript texts and metadata. We use CEASR to evaluate the quality of ASR systems by calculating an average Word Error Rate (WER) per corpus, per system and per corpus-system pair. Our experiments show a substantial difference in accuracy between commercial versus open-source ASR tools as well as differences up to a factor ten for single systems on different corpora. Using CEASR allowed us to very efficiently and easily obtain these results. Our corpus enables researchers to perform ASR-related evaluations and various in-depth analyses with noticeably reduced effort, i.e. without the need to collect, process and transcribe the speech data themselves.

In this digital age of the computer, Internet, and social media and Internet of Things, e-assessments have become an accepted method to determine if students have learned materials presented in a course. With acceptance of this electronic means of assessing students, many questions arise about this method. What should be the format of e-assessment? What amount of time? What kinds of questions should be asked (multiple choice, short answer, etc.)? These are only a few of the many different questions. In addition, educators have always had to contend with the possibility that some students might cheat on an examination. It is widely known that students are often times more technologically savvy than their professors. So how does one prevent students from cheating on an e-assessment? Understandably, given the amount of information available on e-assessments and the variety of formats to choose from, choosing to administer e-assessments over paper-based assessments can lead to confusion on the part of the professor. This paper presents helpful guidance for lecturers who want to introduce e-assessments in their class, and it provides recommendations about the technical infrastructure to implement to avoid students cheating. It is based on literature review, on an international survey that gathers insights and experiences from lecturers who are using e-assessment in their class, and on technological evaluation of e-assessment infrastructure.

In the literature about association analysis, many interestingness measures have been proposed to assess the quality of obtained association rules in order to select a small set of the most interesting among them. In the particular case of hierarchically organized items and generalized association rules connecting them, a measure that dealt appropriately with the hierarchy would be advantageous. Here we present the further developments of a new class of such hierarchical interestingness measures and compare them with a large set of conventional measures and with three hierarchical pruning methods from the literature. The aim is to find interesting pairwise generalized association rules connecting the concepts of multiple ontologies. Interested in the broad empirical evaluation of interestingness measures, we compared the rules obtained by 37 methods on four real world data sets against predefined ground truth sets of associations. To this end, we adopted a framework of instance-based ontology matching and extended the set of performance measures by two novel measures: relation learning recall and precision which take into account hierarchical relationships.

This paper presents a data mining system for multi-label classification and hierarchy extraction from the predictions provided by a multi-label classifier. Classes in multi-label classification tasks are often hierarchically organized and the hierarchy is assumed to be known. A much less investigated approach and a more challenging task, however, is to suppose that the underlying class taxonomy is unknown and that a data mining system can infer it automatically. In our setting, the proposed system is trained with multi-label data and is subsequently able to produce multi-label predictions along with hierarchical relationships between classes. The hierarchy extraction algorithm is based on building association rules from label co-occurrences. Within the framework we examine the performance of two recently introduced multi-label extensions of Adaptive Resonance Theory (ART)-based neural networks: Multi-Label Fuzzy ARTMAP (ML-FAM) and Multi- Label Fuzzy Adaptive Resonance Associative Map (ML-ARAM) in comparison with two state-of-the-art classifiers Multi-Label k-Nearest Neighbors (ML-kNN) and BoosTexter, taking into account the quality of hierarchy extraction. We also develop a novel distance measure for the quantitative evaluation of the derived class hierarchies and compare it with two other distance measures. To demonstrate the effectiveness of the proposed approach, experiments on several benchmark datasets have been performed.