Browsing Han Publications by Author "Sappelli, M."

Now showing items 1-13 of 13

Children, Co-creation and Content Generating AI’s Towards an understanding of co-creating with children and content generating AI’s
Sappelli, M. ; Sluis-Thiescheffer, W.
2022, Article in monograph or in proceedings (NordiCHI workshop - Age against the machine: A Call for Designing Ethical AI for and with Children)With the development of content-generating Artificial Intelligence (AI) systems, such as generating images from a textual description, new possibilities for using such system in design processes arise. In this position paper, we argue that we need to explicitly incorporate children's values when we develop design methods that incorporate content-generating AI to protect their creative processes. In a mini-inquiry we find that children from different ages have articulate ideas about being in the same design space as a content-generating AI’s. They share concerns about fidelity, transparency and how it changes the level-playing field for them. To setup a safe and ethical design space when co-creating with children we foresee three important steps: 1) explore the value of children with respect to content-generation AI. 2) improve the accessibility of these systems for children and 3) study the effect of using such a system on creativity and innovation in a design process.
Development and internal validation of a machine learning prediction model for low back pain non-recovery in patients with an acute episode consulting a physiotherapist in primary care
Knoop, J. ; Lankveld, W.G.J.M. van ; Beijer, L.J. ; Geerdink, F.J.B ; Heymans, M.W. ; Hoogeboom, T.J. ; Hoppenbrouwers, S.J.B.A. ; van Overmeeren, E. ; Soer, R ; Veenhof, C. ; Vissers, K.C.P ; van der Wees, P. J. ; Sappelli, M. ; Staal, J.B. et al. sine al.
2022, Article / Letter to editor (BMC Musculoskeletal Disorders, (2022))Background While low back pain occurs in nearly everybody and is the leading cause of disability worldwide, we lack instruments to accurately predict persistence of acute low back pain. We aimed to develop and internally validate a machine learning model predicting non-recovery in acute low back pain and to compare this with current practice and ‘traditional’ prediction modeling. Methods Prognostic cohort-study in primary care physiotherapy. Patients (n = 247) with acute low back pain (≤ one month) consulting physiotherapists were included. Candidate predictors were assessed by questionnaire at baseline and (to capture early recovery) after one and two weeks. Primary outcome was non-recovery after three months, defined as at least mild pain (Numeric Rating Scale > 2/10). Machine learning models to predict non-recovery were developed and internally validated, and compared with two current practices in physiotherapy (STarT Back tool and physiotherapists’ expectation) and ‘traditional’ logistic regression analysis. Results Forty-seven percent of the participants did not recover at three months. The best performing machine learning model showed acceptable predictive performance (area under the curve: 0.66). Although this was no better than a’traditional’ logistic regression model, it outperformed current practice. Conclusions We developed two prognostic models containing partially different predictors, with acceptable performance for predicting (non-)recovery in patients with acute LBP, which was better than current practice. Our prognostic models have the potential of integration in a clinical decision support system to facilitate data-driven, personalized treatment of acute low back pain, but needs external validation first.
Truth or Error? Towards systematic analysis of factual errors in abstractive summaries
Lux, K. ; Sappelli, M. ; Larson, M.
2020, Article in monograph or in proceedings (Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems)
Data Science for Smart Grids
Sappelli, M. ; Nguyen, T. ; Asare-Bediako, B. ; Westra, J.M. ; Hoppenbrouwers, S.J.B.A.
2020, External research report
BERT-NL a set of language models pre-trained on the Dutch SoNaR corpus
Brandsen, A. ; Dirkson, A. ; Verberne, S. ; Sappelli, M. ; Manh Chu, D ; Stoutjesdijk, K.
2019, Article in monograph or in proceedings (Dutch-Belgian Information Retrieval Conference (DIR 2019))
Personalized support for well-being at work: an overview of the SWELL project
Kraaij, W. ; Verberne, S. ; Koldijk, S ; Korte, E de ; Dantzig, S van ; Sappelli, M. ; Shoaib, M. ; Bosems, S. ; Achterkamp, R. ; Bonomi, A. ; Schavemaker, J. ; Hulsebosch, B. ; Wabeke, T. ; Vollenbroek-Hutten, M. ; Neerincx, M. ; Sinderen, M. van et al. sine al.
2019, Article / Letter to editor (User Modeling and User-Adapted Interaction, (2019), pp. 1-34)
"let me tell you who you are" - Explaining recommender systems by opening black box user profiles
Graus, D. ; Sappelli, M. ; Manh Chu, D
2018, Article in monograph or in proceedings (The 2nd fatrec workshop on responsible recommendation)Personalization of media services is gaining more and more traction, e.g., through the rise of personalization driven by recommender systems across media outlets. At the same time, we see a general rise in distrust and skepticism around the collection and processing of personal data, spurred by policy changes such as the introduc- tion of the GDPR, data breach incidents, and the rise of privacy concerns in general. We feel it is of central importance to be trans- parent about the information we collect, and the ways we use it. In this position paper we motivate the importance of enabling transparency through explaining our recommender system. More specifically, we aim to explain the inferred user profiles that are cen- tral to content-based recommender systems. We describe how user profile explanations can contribute to, or enable different aspects of our recommender system; transparency to help users better under- stand the inner workings of the recommender system, scrutability to allow users to provide explicit feedback on the internally con- structed user profiles, and self-actualization to support users in understanding and exploring their personal preferences. Finally, we believe that user profile explanations can find novel and interesting explanations as an end in itself.
Smart journalism: personalizing, summarizing, and recommending financial economic news
Sappelli, M. ; Manh Chu, D ; Cambel, B. ; Graus, D. ; Bressers, P.
2018, Article in monograph or in proceedings (The algorithmic personalization and news (apen18) workshop at icwsm '18)FD Mediagroep (FDMG1 ) is the leading information provider in the financial economic domain in the Netherlands. FDMG operates “Het Financieele Dagblad” (FD) a daily finan- cial newspaper, similar to the Financial Times. In addition, FDMG operates the daily all-news radio station “Business News Radio” (BNR). As we have a wide variety of users with various backgrounds and interests, we believe that digital me- dia (both news articles and radio) should be personalized to match the interests of a particular customer. We are therefore working on personalization of FDMG’s digital media: • Personalized news: Recommendations and personalized summaries of news articles that match the reading pref- erences and interests of our readers • Personalized radio: A non-linear radio experience with ra- dio snippets that match the listener’s interests In both personalized news and personalized radio we are looking not only at introducing recommender systems but also at personalized ways to present the information using automated summarization (news) and audio segmentation (ra- dio) methods
Smart radio: personalized news radio
Sappelli, M. ; Manh Chu, D ; Cambel, B. ; Nortier, J. ; Graus, D.
2018, Article in monograph or in proceedings (The 17th dutch-belgian information retrieval workshop)In this demonstration paper we describe the SMART Radio app 1 forBNRNieuwsradio. TheSMARTRadioappisanextensionto the current BNR app, which offers users a more personalized news radio experience. It does so by automatically fragmenting shows to offer our users more targeted and focused fragments of audio, not full shows. We employ audio segmentation and audio topic- tagging techniques to achieve this, which we describe in this paper. In its present form, users can subscribe to tags to get appropriate suggestions of relevant radio fragments. In the future we would like to improve the app’s personalization, by using information of the user’s interaction with the app.
Investigating the interpretability of hidden layers in deep text mining
Raaijmakers, S. ; Sappelli, M. ; Kraaij, W.
2017, Article in monograph or in proceedings (Proceedings of the 13th International Conference on Semantic Systems)In this short paper, we address the interpretability of hidden layer representations in deep text mining: deep neural networks applied to text mining tasks. Following earlier work predating deep learning methods, we exploit the internal neural network activation (latent) space as a source for performing k-nearest neighbor search, looking for representative, explanatory training data examples with similar neural layer activations as test inputs. We deploy an additional semantic document similarity metric for establishing document similarity between the textual representations of these nearest neighbors and the test inputs. We argue that the statistical analysis of the output of this measure provides insight to engineers training the networks, and that nearest neighbor search in latent space combined with semantic document similarity measures offers a mechanism for presenting explanatory, intelligible examples to users.
A vision on Prescriptive Analytics
Sappelli, M. ; Boer, M. de ; Smit, S. ; Bomhof, F.
2017, Article in monograph or in proceedings (Proceedings of ALLDATA, The 3d international conference on Big Data, Small Data, Linked Data and Open Data)In this paper, we show our vision on prescriptive analytics. Prescriptive analytics is a field of study in which the actions are determined that are required in order to achieve a particular goal. This is different from predictive analytics, where we only determine what will happen if we continue current trend. Consequently, the amount of data that needs to be taken into account is much larger, making it a relevant big data problem. We zoom in on the requirements of prescriptive analytics problems: impact, complexity, objective, constraints and data. We explain some of the challenges, such as the availability of the data, the downside of simulations, the creation of bias in the data and trust of the user. We highlight a number of application areas in which prescriptive analytics could or would not work given our requirements. Based on these application areas, we conclude that domains with a large amount of data and in which the phenomena are restricted by laws of physics or math are very applicable for prescriptive analytics. Areas in which the human or human activities play a role, future research will be required to meet the requirements and tackle the challenges. Directions of future research will be in integrating model-driven and data-driven approaches, but also privacy, ethics and legislation. Whereas predictive analytics is often already accepted in society, prescriptive analytics is still in its infancy.
Analyzing cancer forum discussions with text mining
Oortmerssen, G. van ; Raaijmakers, S. ; Sappelli, M. ; Boertjes, E. ; Verberne, S. ; Walasek, N. ; Kraaij, W.
2017, Article in monograph or in proceedings (2nd International Workshop on Extraction and Processing of Rich Semantics from Medical Texts)We present a multilingual, open source system for cancer forum thread analysis, equipped with a biomedical entity tagger and a module for textual summarization. This system allows users to investi- gate textual co-occurrences of biomedical entities in forum posts, and to browse through summaries of long discussions. It is applied to a number of online cancer patient fora, including a gastro-intestinal cancer forum and a breast cancer forum. We propose that the system can serve as an extra source of information for medical hypothesis formulation, and as a facility for boosting patient empowerment.
Knowledge Work in Context: User Centered Knowledge Worker Support
Sappelli, M.
2016, Dissertation

Now showing items 1-13 of 13

Browsing Han Publications by Author "Sappelli, M."

Browse

All of HAN Publications

This Collection