July 8–11, 2018 Singapore

UMAP’18 Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization Sponsored by: ACM SIGCHI & ACM SIGWEB General Chairs: Tanja Mitrovic (University of Canterbury, New Zealand) Jie Zhang (Nanyang Technological University, Singapore) Program Chairs: Li Chen (Hong Kong Baptist University, China) David Chin (University of Hawaii, USA)

The Association for Computing Machinery 2 Penn Plaza, Suite 701 New York, New York 10121-0701

Copyright © 2018 by the Association for Computing Machinery, Inc. (ACM). Permission to make digital or hard copies of portions of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyright for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permission to republish from: [email protected] or Fax +1 (212) 869-0481.

For other copying of articles that carry a code at the bottom of the first or last page, copying is permitted provided that the per-copy fee indicated in the code is paid through www.copyright.com.

Notice to Past Authors of ACM-Published Articles ACM intends to create a complete electronic archive of all articles and/or other material previously published by ACM. If you have written a work that has been previously published by ACM in any journal or conference proceedings prior to 1978, or any SIG Newsletter at any time, and you do NOT want this work to appear in the ACM Digital Library, please inform [email protected], stating the title of the work, the author(s), and where and when published.

ISBN: 978-1-4503-5784-5 480160

Additional copies may be ordered prepaid from:

ACM Order Department Phone: 1-800-342-6626 (USA and Canada) PO Box 30777 +1-212-626-0500 (Global) New York, NY 10087-0777, USA Fax: +1-212-944-1318 E-mail: [email protected] Hours of Operation: 8:30 am – 4:30 pm ET

Printed in the USA

ii Table of Contents

UMAP 2018 Conference Organization ...... x

UMAP’18 Sponsor & Supporters ...... xiv

Workshops & Tutorials Chair Welcome  UMAP’18 Workshop & Tutorial Chairs’ Welcome (overview) & Organization List ...... 1 Marko Tkalčič (Free University of Bozen-Bolzano), Marco de Gemmis ( Aldo Moro)

FairUMAP Workshop  UMAP 2018 Fairness in User Modeling, Adaptation and Personalization (FairUMAP 2018) Chairs’ Welcome & Organization ...... 3 Bamshad Mobasher, Robin Burke (DePaul University), Michael Ekstrand (Boise State University), Bettina Berendt (KU Leuven)  Same, Same, but Different: Algorithmic Diversification of Viewpoints in News ...... 7 Nava Tintarev, Emily Sullivan (TU Delft), Dror Guldin (), Sihang Qiu (Delft), Daan Odjik (Blendle Research)  Compliance of Personalized Radio with Public-Service Remits ...... 15 Stefan Hirschmeier, Vanessa Beule (University of Cologne)  Using Image Fairness Representations in Diversity-Based Re-ranking for Recommendations ... 23 Chen Karako, Putra Manggala (Shopify Inc.)  Fairness In Reciprocal Recommendations: A Speed-Dating Study ...... 29 Yong Zheng, Tanaya Dave, Neha Mishra, Harshit Kumar (Illinois Institute of Technology)  Diversity Checker: Toward Recommendations for Improving Journalism with Respect to Diversity ...... 35 Jeroen Peperkamp, Bettina Berendt (KU Leuven)

HAAPIE Workshop  UMAP 2018 HAAPIE (Human Aspects in Adaptive and Personalized Interactive Environments) Workshop Chairs’ Welcome & Organization ...... 43 Panagiotis Germanakos (SAP SE & University of ), Styliani Kleanthous-Loizou, George Samaras (University of Cyprus), Vania Dimitrova (), Ben Steichen (California State Polytechnic University, Pomona), Alicja Piotrkowicz (University of Leeds)  Your Digital News Reading Habits Reflect Your Personality ...... 45 Marios Constantinides (University College London), Panagiotis Germanakos (SAP SE and University of Cyprus), George Samaras (University of Cyprus), John Dowell (University College London)  Exploring User Roles In Group Recommendations: A Learning Approach ...... 49 Yong Zheng (Illinois Institute of Technology)  Towards a Fuzzy Rule-based Systems Approach for Adaptive Interventions in Menopause Self-care ...... 53 Amaury Trujillo (IIT-CNR & Università di Pisa), Maria Claudia Buzzi (IIT-CNR)  Equilibrium State of Interaction: Maximizing User Experience through Optimum Adaptivity States...... 57 Panagiotis Germanakos (SAP SE & University of Cyprus), Panayiotis Andreou (UCLan Cyprus & InSPIRE Research Center), Constantinos Mourlas (University of Athens)  Self-Regulation, Knowledge, Experience: Which User Characteristics are Useful for Predicting Video Engagement? ...... 63 Alicja Piotrkowicz, Vania Dimitrova (University of Leeds), Antonija Mitrovic (University of Canterbury), Lydia Lau (University of Leeds)  Towards Modelling the User Creative Process in a Sandbox Game ...... 69 Styliani Kleanthous, Demetris Christodoulou, George A. Papadopoulos, George Samaras (University of Cyprus)

vi  A Survey on Different Means of Personalized Dialog Output for an Adaptive Personal Assistant ...... 75 Maria Schmidt, Patricia Braunger (Daimler AG)  User Modelling in Exergames for Frail Older Adults ...... 83 Zelai Sáenz-de-Urturi (Artificial Intelligence Dept. UNED), Olga C. Santos (aDeNu Research Group. Artificial Intelligence Dept. UNED),

HUM Workshop  UMAP 2018 HUM (Holistic User Modeling) Workshop Chairs’ Preface & Organization ...... 87 Cataldo Musto (University of Bari), Amon Rapp, Federica Cena (University of Torino), Frank Hopfgartner (University of Sheffield), Judy Kay (University of Sydney), Giovanni Semeraro (University of Bari)  Tourist Support System Using User Context Obtained from a Personal Information Device ... 91 Shogo Matsuno (Toyohashi University of Technology & Hotto Link, Inc.), Reiji Suzumura, Minoru Ohyama (Tokyo Denki University)  A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints ...... 97 Cataldo Musto, Giovanni Semeraro, Cosimo Lovascio, Marco de Gemmis, Pasquale Lops (University of Bari Aldo Moro)  iSynchronizer: A Tool for Extracting, Integration and Analysis of MovieLens and IMDb Datasets ...... 103 Nourah A. ALRossais, Daniel Kudenko (University of York)  Holistic User Models for Cognitive Disabilities: Personalized Tools for Supporting People with Autism in the City ...... 109 Amon Rapp, Federica Cena, Claudio Mattutino, Alessia Calafiore, Claudio Schifanella, Elena Grassi, Guido Boella (University of Torino)  Me, Myself and I: Are Looking for a Balance between Personalization and Privacy ...... 115 Esma Aïmeur, Alexis Tremblay (Université de Montréal)  Interactive Recommendations by Combining User-Item Preferences with Linked Open Data ...... 121 Surya Kallumadi, William H. Hsu (Kansas State University)  Injecting Semantic Diversity in Top-N Recommender Systems Using Determinantal Point Processes and Curated Lists ...... 127 Surya Kallumadi, Gabriel Necoechea (Kansas State University)  Predicting Learning Difficulty Based on Gaze and Pupil Response ...... 131 Saurin Parikh (Florida Atlantic University & Nirma University), Hari Kalva (Florida Atlantic University)

IUadaptMe Workshop  UMAP 2018 Intelligent User-Adapted Interfaces: Design and Multi-Modal Evaluation (IUadaptMe) Workshop Chairs’ Welcome & Organization ...... 137 Ilknur Celik (Cyprus International University), Ilaria Torre, Frosina Koceva (University of Genoa), Christine Bauer (Johannes Kepler University Linz), Eva Zangerle (Universität Innsbruck), Bart Knijnenburg (Clemson University)  Adaptive User Interface for a Personalized Mobile Banking App: Extended Abstract ...... 141 Mohammad Nawaz, Luvai Motiwalla, Amit V. Deokar (University of Massachusetts, Lowell)  User Acceptance of Proactive Recommendations on Smartphone and Smartwatch ...... 143 Michael Bub, Evgeny Volynsky, Wolfgang Wörndl (Technical University of Munich)  Modeling User Intents as Context in Smartphone-connected Hearing Aids ...... 151 Maciej Jan Korzepa, Benjamin Johansen (Technical University of Denmark), Michael Kai Petersen (Eriksholm Research Center), Jan Larsen, Jakob Eg Larsen (Technical University of Denmark), Niels Henrik Pontoppidan (Eriksholm Research Center)  Comparing Sequential and Temporal Patterns from Human Mobility Data for Next-Place Prediction ...... 157 Yunlong Wang, Corinna Breitinger, Björn Sommer, Falk Schreiber, Harald Reiterer (University of Konstanz)

vii RESEARCH-ARTICLE UMAP  Predicting Learning Diculty Based on Gaze and Pupil Response     

Authors: Saurin Parikh, Hari Kalva Authors Info & Aliations

Publication: UMAP '18: Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization • July 2018 • Pages 131–135 • https://doi.org/10.1145/3213586.3226224

 1  99

    eReader  PDF

17        

ABSTRACT

E-Learning is transforming the way education is imparted. Today, millions of students take self-paced online courses. However, the content and language complexity often hinders comprehension and this together with lack of immediate help from the course instructor leads to weak learning outcomes. Ability to predict dicult content in real time enables eLearning systems to adapt content as per students' level of learning. The recent introduction of low-cost eye trackers has opened the new class of applications based on eye response. Eye tracking devices can record eye response to the visual element or concept causing a learning diculty. The response and the variations in eye response to the same concept over time may be indicative of the level of learning. In this paper, we use eye movement measures to predict the levels of learning associated with a term/concept. The main contribution of this study is the spatio-temporal analysis of eye response to a term/concept. Proposed system analyses slide images, extracts words (terms), maps the eye response to words, and prepares a term- respoFeedbacknse map. A majority voting classier trained with terms of known learning levels uses this term response map to classify a term as novel or familiar. The proposed system achieves 61% accuracy when predicting learning diculty.

References UMAP  1. C. Conati and C. Merten, "Eye-tracking for user modeling in exploratory learning environments: An empirical evaluation," Knowl.-Based Syst., vol. 20, no. 6, pp. 557--574, Aug. 2007.

2. V. Manuel et al., "AdeLE: A Framework for Adaptive E-Learning through Eye Tracking," in Proceedings of IKNOW 2004, 2004, pp. 609--616.

3. C. Calvi, M. Porta, and D. Sacchi, "e5Learning, an E-Learning Environment Based on Eye Tracking," in 2008 Eighth IEEE International Conference on Advanced Learning Technologies, 2008, pp. 376--380.

Show All References

Index Terms

Predicting Learning Diculty Based on Gaze and Pupil Response

Applied computing Human-centered computing

Education Human computer interaction (HCI)

E-learning HCI theory, concepts and models

Comments

Feedback HUM Workshop UMAP’18 Adjunct, July 8–11, 2018, Singapore, Singapore

Predicting Learning Difficulty based on Gaze and Pupil Response

Saurin Parikh Hari Kalva Florida Atlantic University Institute of Technology, Florida Atlantic University Boca Raton Nirma University Boca Raton Florida Ahmedabad Florida USA Gujarat USA [email protected] India [email protected] [email protected]

ABSTRACT E-Learning is transforming the way education is imparted. Today, INTRODUCTION millions of students take self-paced online courses. However, the content and language complexity often hinders comprehension Today's eLearning and this together with lack of immediate help from the course E-Learning has transformed the way education is delivered to instructor leads to weak learning outcomes. Ability to predict students across the globe. E-learning classrooms have a diverse difficult content in real time enables eLearning systems to adapt group of students from various demographics. Self-paced learning content as per students' level of learning. The recent introduction is a popular eLearning model, and its primary challenge is the of low-cost eye trackers has opened the new class of applications based on eye response. Eye tracking devices can record eye teachers' unavailability to address a student’s learning concern response to the visual element or concept causing a learning when it is needed the most. Due to this reason, a student needs to difficulty. The response and the variations in eye response to the look for answers/solutions from other sources, causing delay and same concept over time may be indicative of the level of learning. interruptions in learning. E-learning platforms need to adapt to a In this paper, we use eye movement measures to predict the levels student's learning level. Such content adaptation requires ability of learning associated with a term/concept. The main contribution to predict in real time the content (visual elements or concepts) of this study is the spatio-temporal analysis of eye response to a causing learning difficulty. Cognition of content is student- term/concept. Proposed system analyses slide images, extracts specific and dependent on readers' skills such as logical reasoning, words (terms), maps the eye response to words, and prepares a quantitative analysis, and verbal skills. These skills vary because term-response map. A majority voting classifier trained with of demographics, culture, experience, education and biological terms of known learning levels uses this term response map to classify a term as novel or familiar. The proposed system achieves factors such as cognition, working memory capacity, 61% accuracy when predicting learning difficulty. psychomotor skills, oculomotor dysfunctions, and reading disorders. Ability to predict students' understanding of content CCS Concepts (i.e. difficult term/concept), in real time, enables e-learning • Human-centered computing → Human computer interaction (HCI) → HCI systems to adapt content, provide supplementary learning content theory, concepts and models; Applied computing → Education → E-learning and classify readers into various learning groups by their level. KEYWORDS Recent developments have made it possible to use compact and Predicting levels of learning; eye movement analysis; pupillary response low-cost eye trackers to track eye movements and pupil response analysis; e-learning; predicting learning difficulty; eye tracking (collectively referred to in this paper as eye response). Eye trackers give the gaze coordinates of the readers which can be ACM Reference format: used to locate the exact visual element (text, the graphic on Saurin Parikh and Hari Kalva. 2018. Predicting Learning Difficulty based display) that is causing the response. We hypothesize that on Gaze and Pupil Response. In Proceedings of UMAP'18 Adjunct, July 8 variations in eye response to the same concept over time may be 11, 2018, Singapore, Singapore, 5 pages. indicative of levels of learning and may help to detect the exact https://doi.org/10.1145/3213586.3226224 visual element causing learning difficulty. The proposed approach Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed is to do the spatio-temporal analysis of the eye responses to for profit or commercial advantage and that copies bear this notice and the full predict learning difficulty. citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific Research Studies permission and/or a fee. Request permissions from [email protected]. UMAP'18 Adjunct, July 8–11, 2018, Singapore, Singapore The earlier research uses various eye movement measures to © 2018 Association for Computing Machinery. assess the learner's cognitive response. Conati et al. [1] proposed ACM ISBN 978-1-4503-5784-5/18/07…$15.00 https://doi.org/10.1145/3213586.3226224 a model that uses eye-tracking data to determine the reader's

131