In this study, we compared the impact of audio-, video-, and text-chat interaction on target language use during online learner-learner interaction and on learner affect amongst adolescent learners of German as a foreign language. Repeated measures and ANOVA analyses revealed a high percentage of target language output in all conditions for all four tasks, especially in text- chat. Audio-chatters produced the most output and used the most meaning negotiation, compensation strategies, self-repair and other-repair strategies. Learners in all conditions gained in enjoyment, willingness to communicate and self-efficacy. Anxiety reduced for text-chatters. Task effects partly determined the quantity of L2 output, while condition effects determined meaning-oriented and form-focused processing.
MULTIFILE
Objective: To annotate a corpus of randomized controlled trial (RCT) publications with the checklist items of CONSORT reporting guidelines and using the corpus to develop text mining methods for RCT appraisal. Methods: We annotated a corpus of 50 RCT articles at the sentence level using 37 fine-grained CONSORT checklist items. A subset (31 articles) was double-annotated and adjudicated, while 19 were annotated by a single annotator and reconciled by another. We calculated inter-annotator agreement at the article and section level using MASI (Measuring Agreement on Set-Valued Items) and at the CONSORT item level using Krippendorff's α. We experimented with two rule-based methods (phrase-based and section header-based) and two supervised learning approaches (support vector machine and BioBERT-based neural network classifiers), for recognizing 17 methodology-related items in the RCT Methods sections. Results: We created CONSORT-TM consisting of 10,709 sentences, 4,845 (45%) of which were annotated with 5,246 labels. A median of 28 CONSORT items (out of possible 37) were annotated per article. Agreement was moderate at the article and section levels (average MASI: 0.60 and 0.64, respectively). Agreement varied considerably among individual checklist items (Krippendorff's α= 0.06–0.96). The model based on BioBERT performed best overall for recognizing methodology-related items (micro-precision: 0.82, micro-recall: 0.63, micro-F1: 0.71). Combining models using majority vote and label aggregation further improved precision and recall, respectively. Conclusion: Our annotated corpus, CONSORT-TM, contains more fine-grained information than earlier RCT corpora. Low frequency of some CONSORT items made it difficult to train effective text mining models to recognize them. For the items commonly reported, CONSORT-TM can serve as a testbed for text mining methods that assess RCT transparency, rigor, and reliability, and support methods for peer review and authoring assistance. Minor modifications to the annotation scheme and a larger corpus could facilitate improved text mining models. CONSORT-TM is publicly available at https://github.com/kilicogluh/CONSORT-TM.
'The Data Tales' is een langdurig samenwerkingsverband van onderzoekers en bedrijven die samen projecten uitvoeren en vragen beantwoorden als: hoe kan data ons helpen de relatie met klanten te verbeteren en hoe beschermen we privacy van de klant als we die klant ook beter van dienst zijn willen zijn met data technieken?Doel The Data Tales consortium wil bedrijven helpen om beter met hun klanten om te gaan. Want als bedrijven naar hun klanten luisteren, versterken ze hun band. Techniek biedt allerlei opties om sneller, gerichter en zinvoller te reageren op de behoeften van klanten. Daarbij moeten de toon, inhoud en presentatie van de boodschap aansluiten bij de geadresseerde. Het doel van The Data Tales is om samen met onderwijs, bedrijven en technologie-ontwikkelaars te werken aan technieken om direct inzicht te geven in hoe hun klanten de interactie met organisaties ervaren. Daarbij wordt altijd gewerkt volgens het principe 'ethics by design' Resultaten Consortium The Data Tales vormde de basis voor het KIEM-project, VERBIND. Dat staat voor verantwoorde, belevingsgerichte interactie op basis van data-analyse. VERBIND brengt meerdere invalshoeken samen. We kijken niet alleen naar wat technisch mogelijk is bij dataverzameling, maar ook naar ethische keuzes die bedrijven maken. Op thedatatales.org lees je meer over het project VERBIND. Looptijd 01 januari 2018 - 31 december 2020 Aanpak In het Data Tales consortium komen de volgende vakgebieden samen: Customer Journey & marketing Data Science, waaronder process mining, text mining en andere vormen van data mining Recht en Ethiek, waaronder AVG Gedragswetenschappen ICT
In order to stay competitive and respond to the increasing demand for steady and predictable aircraft turnaround times, process optimization has been identified by Maintenance, Repair and Overhaul (MRO) SMEs in the aviation industry as their key element for innovation. Indeed, MRO SMEs have always been looking for options to organize their work as efficient as possible, which often resulted in applying lean business organization solutions. However, their aircraft maintenance processes stay characterized by unpredictable process times and material requirements. Lean business methodologies are unable to change this fact. This problem is often compensated by large buffers in terms of time, personnel and parts, leading to a relatively expensive and inefficient process. To tackle this problem of unpredictability, MRO SMEs want to explore the possibilities of data mining: the exploration and analysis of large quantities of their own historical maintenance data, with the meaning of discovering useful knowledge from seemingly unrelated data. Ideally, it will help predict failures in the maintenance process and thus better anticipate repair times and material requirements. With this, MRO SMEs face two challenges. First, the data they have available is often fragmented and non-transparent, while standardized data availability is a basic requirement for successful data analysis. Second, it is difficult to find meaningful patterns within these data sets because no operative system for data mining exists in the industry. This RAAK MKB project is initiated by the Aviation Academy of the Amsterdam University of Applied Sciences (Hogeschool van Amsterdan, hereinafter: HvA), in direct cooperation with the industry, to help MRO SMEs improve their maintenance process. Its main aim is to develop new knowledge of - and a method for - data mining. To do so, the current state of data presence within MRO SMEs is explored, mapped, categorized, cleaned and prepared. This will result in readable data sets that have predictive value for key elements of the maintenance process. Secondly, analysis principles are developed to interpret this data. These principles are translated into an easy-to-use data mining (IT)tool, helping MRO SMEs to predict their maintenance requirements in terms of costs and time, allowing them to adapt their maintenance process accordingly. In several case studies these products are tested and further improved. This is a resubmission of an earlier proposal dated October 2015 (3rd round) entitled ‘Data mining for MRO process optimization’ (number 2015-03-23M). We believe the merits of the proposal are substantial, and sufficient to be awarded a grant. The text of this submission is essentially unchanged from the previous proposal. Where text has been added – for clarification – this has been marked in yellow. Almost all of these new text parts are taken from our rebuttal (hoor en wederhoor), submitted in January 2016.
Within the food industry there is a need to be able to rapidly react to changing regulatory requirements and consumer preferences by adjusting recipes, processes, and products. A good knowledge of the properties of food ingredients is crucial in this process. Currently this knowledge is available in scattered heterogeneous resources such as scientific peer-reviewed articles, databases, recipes, food blogs as well as in the experience of food-experts. This prevents, in practice, the efficient integration and use of this knowledge, leading to inefficiency and missed opportunities. In this project we will build a structured database of properties of food ingredients, focusing in particular on the taste and texture properties. By large-scale collection and text mining on a large number of textual resources, a comprehensive data set on ingredient properties will be created, along with knowledge on the relationships between these ingredients. This database will then be used for to find new potential applications for healthy and taste enhancing ingredient combinations by network-based discovery methods and artificial intelligence algorithms will be used. A concrete focus will be on application questions formulated by the industrial partners. The resulting hypothesis will be validated in a real life setting at the premises of the industrial partners. The deliverables of this project will be: - A reusable open-access ingredient database that is accessible via a user-friendly web portal - A set of state-of-the-art mining algorithms that can address a wide variety of industry driven use cases - Novel product formulations that can be further developed for the consumer and business2business market
