Markus Reiter-Haas

Postdoctoral Researcher @ Graz University of Technology

Institute of Human-Centred Computing Sandgasse 36/III, 8010 Graz Austria

About Me

Dr. Markus Reiter-Haas is a researcher dedicated to the optimization of modern socio-technical platforms. My work integrates User Behavior Analysis, Representation Learning, and Ethical Matching Algorithms to create more reliable Information Retrieval and Recommender Systems. Currently investigating how neuro-symbolic approaches can foster trustworthy content diversification and mitigate polarization in large-scale information systems.

Research Interests

recommender systems, information retrieval, artificial intelligence, natural language processing, computational social science, Transformers, user modeling and item representations

Experience

since 2025 Postdoctoral University Project Assistant
Graz University of Technology
Researching Neurosymbolic AI and ethical recommender systems

2024-2025 Postdoctoral Associate
Duke University
The Polarization Lab (Joint Lab of the department of Statistical Science, Political Science, and Sociology)

2020–2024 University Assistant
Graz University of Technology
Research Focus: NLP in Social Systems

2017-2020 Data Scientist
Moshbit GmbH (Talto - Talents of Tomorrow)
Research on deeplearning for job recommenders
Funded by FFG (national funding agency)

2013-2017 Student Assistant
Graz University of Technology
Fundementals in Computer Science

2011-2012 Civilian Service
Emergency call dispatching for fire brigades

2008-2010 Summer Internships
GUEP (2010), Joanneum Research (2009), Siemens (2008)

Education

2020-2024 PhD in Computer Science
Graz University of Technology
Thesis: “Computational Framing Analysis for Polarized Topics Online”
Passed with distinction

2017–2020 Master in Computer Science
Graz University of Technology
Thesis: “Evaluation of Job Recommendations for the Studo Jobs Platform” Main Specialization: Knowledge Technologies
Secondary Specialization: Multimedia Information Systems
Passed with distinction

2012–2017 Bachelor in Computer Science
Graz University of Technology
Catrobat Project: Timesheet Plugin for Jira
Passed with distinction

2006–2011 Technical College in Computer Science
HTBLA Kaindorf an der Sulm
Passed with distinction

Teaching

2025W Advanced Information Retrieval
Guest lecture on Transformers for Information Retrieval

2025 Human-AI Co-Evolution
Guest lecture Lecture unit on the Social Media Accelerator platform for studying human behavior with field experiments on using LLM-powered bots.

2022W-2023W Advanced Information Retrieval
Lecturer WS23 (PyTorch 4 Deeplearning, Transformers 4 IR - Reranking and Retrieval)
Lecturer WS22 (Transformer 4 IR Hands-on Tutorial)
Projects WS22 (Showcase) and WS23 (Showcase)

2022W-2023W Research Meetings within the Recommender Systems and Social Computing Lab
Organization, Unit on academic publishing

2022W SemEval 2023 Challenge Team
1st place on Spanisch Framing Detection

2021W Web Technology
Practicals + Lecture Unit

2021S Social Media Course @ Uni Graz
Guest Lecture
Social Media and Digital Trace Data

2020S Know-Center Summer School
Invited Speaker
Polarization

Co-Supervision

2023S Alexander Ertl - Master Thesis
Contrastive Pre-Training of Transformer Models for Computational Framing Analysis

2022W Lukas Preitler - Bachelor Thesis
Topic Description: Word Embedding Association Test to Reveal Gender Bias in Austrian Teaching Literature

Languages

German: Native
English: C1
Python: 10+ years
JavaScript: 10+ years
Java: 15 years

Research

Publications

2025

Reiter-Haas, M., & Lex, E. (2025).
Towards Multi-Aspect Diversification of News Recommendations Using Neuro-Symbolic AI for Individual and Societal Benefit.

Hadler, M., Ertl, A., Klösch, B., Reiter-Haas, M., & Lex, E. (2025).
The climate gluing protests: analyzing their development and framing in media since 1986 using sentiment analyses and frame detection models.
Frontiers in Big Data, 8, 1569623.

2024

Reiter-Haas, M. (2024).
Computational Framing Analysis for Polarized Topics Online.
PhD thesis.

Klösch, B., Hadler, M., Reiter-Haas, M., & Lex, E. (2024).
Polarized opinions on Covid-19 and environmental policy measures. The role of social media use and personal concerns in German-speaking countries.
Innovation: The European Journal of Social Science Research, 37(4), 941-964.

Kowald, D., Reiter-Haas, M., Kopeinik, S., Schedl, M., & Lex, E. (2024).
Transparent Music Preference Modeling and Recommendation with a Model of Human Memory Theory.
In A Human-Centered Perspective of Intelligent Personalized Environments and Systems (pp. 113-136). Cham: Springer Nature Switzerland.

Reiter-Haas, M., Klösch, B., Hadler, M., & Lex, E. (2024).
Computational Narrative Framing: Towards Identifying Frames through Contrasting the Evolution of Narrations.
In Proceedings of the Text2Story’24 Workshop, Glasgow (Scotland), 24-March-2024.

Reiter-Haas, M., & Lex, E. (2024).
The Framing Loop: Do Users Repeatedly Read Similar Framed News Online?
In Joint Proceedings of the ACM IUI Workshops 2024, March 18-21, 2024, Greenville, South Carolina, USA.

Reiter-Haas, M., Klösch, B., Hadler, M., & Lex, E. (2024).
FrameFinder: Explorative Multi-Perspective Framing Extraction from News Headlines.
In Proceedings of the 2024 Conference of Human Information Interaction and Retreival (CHIIR ‘24), 381-385.

Reiter-Haas, M., Klösch, B., Hadler, M., & Lex, E. (2024).
Framing Analysis of Health-Related Narratives: Conspiracy versus Mainstream Media.
arXiv preprint arXiv:2401.10030.

2023

Reiter-Haas, M., Ertl, A., Innerebner, K., & Lex, E. (2023).
mCPT at SemEval-2023 Task 3: Multilingual Label-Aware Contrastive Pre-Training of Transformers for Few-and Zero-shot Framing Detection.
In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 941–949, Toronto, Canada. Association for Computational Linguistics.

Reiter-Haas, M. (2023).
Exploration of Framing Biases in Polarized Online Content Consumption.
Companion Proceedings of the ACM Web Conference 2023, 560–564. Presented at the Austin, TX, USA.

Reiter-Haas, M., Klösch, B., Hadler, M., & Lex, E. (2023).
Polarization of opinions on COVID-19 measures: Integrating Twitter and survey data.
Social Science Computer Review, 41(5), 1811-1835.

Klösch, B., Hadler, M., Reiter-Haas, M., & Lex, E. (2023).
Polarized opinions on Covid-19 and environmental policy measures. The role of social media use and personal concerns in German-speaking countries.
Innovation: The European Journal of Social Science Research, 1-24.

2022

Hadler, M., Klösch, B., Reiter-Haas, M., & Lex, E. (2022).
Combining Survey and Social Media Data: Respondents’ Opinions on COVID-19 Measures and Their Willingness to Provide Their Social Media Account Information.
Frontiers in Sociology, 7.

Klösch, B., Hadler, M., Reiter-Haas, M., & Lex, E. (2022).
Social desirability and the willingness to provide social media accounts in surveys. The case of environmental attitudes.

2021

Reiter-Haas, M., Parada-Cabaleiro, E., Schedl, M., Motamedi, E., Tkalcic, M., & Lex, E. (2021, September).
Predicting Music Relistening Behavior Using the ACT-R Framework.
In Fifteenth ACM Conference on Recommender Systems (pp. 702-707).

Reiter-Haas, M., Kopeinik, S., & Lex, E. (2021, May).
Studying Moral-based Differences in the Framing of Political Tweets.
In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 15, pp. 1085-1089).

Reiter-Haas, M., Klösch, B., Hadler, M., & Lex, E. (2021).
Opinion Polarization on COVID-19 Measures: Integrating Surveys and Social Media Data
(No. 6127). EasyChair.

2020

Reiter-Haas, M., Klösch, B., Hadler, M., & Lex, E. (2020).
Bridging the Gap of Polarization in Public Opinion on Misinformed Topics.
Challenging Misinformation: Exploring Limits and Approaches, workshop co-located with Social Informatics’20

Reiter-Haas, M., Wittenbrink, D., & Lacic, E. (2020, September).
On the Heterogeneous Information Needs in the Job Domain: A Unified Platform for Student Career.
In Fourteenth ACM Conference on Recommender Systems (pp. 573-574).

Reiter-Haas, M. (2020).
Evaluation of Job Recommendations for the Studo Jobs Platform.
MA thesis.

Lacic, E., Reiter-Haas, M., Kowald, D., Dareddy, M. R., Cho, J., & Lex, E. (2020).
Using autoencoders for session-based job recommendations.
In User Modeling and User-Adapted Interaction, 1-42.

2019

Reiter-Haas, M., Lacic, E., Duricic, T., Slawicek, V., & Lex, E. (2019).
Should we Embed? A Study on the Online Performance of Utilizing Embeddings for Real-Time Job Recommendations.
In Proceedings of the 13th ACM Conference on Recommender Systems (pp. 496-500). ACM.

2018

Lacic, E., Kowald, D., Reiter-Haas M., Slawicek, V., & Lex, E. (2018).
Beyond Accuracy Optimization: On the Value of Item Embeddings for Student Job Recommendations.
In the International Workshop on Multi-dimensional Information Fusion for User Modeling and Personalization (IFUP’2018) co-located with the 11th ACM International Conference on Web Search and Data Mining (WSDM’2018)

2017

Reiter-Haas, M., Slawicek, V. & Lacic, E. (2017).
Studo Jobs: Enriching Data With Predicted Job Labels.
In Workshop on Recommender Systems and Social Network Analysis (RS-SNA’2017) co-located with i-KNOW’2017

Awards

2025 Finalist (top 5) for the Advancement Award from the Forum Technik und Gesellschaft to honor dissertations with particular societal relevance.

2023 1st place on Spanisch framing detection at SemEval 2023 task 3.

2022 Best reviewers recognition at the TheWebConf’23 UMAP track.

Funding

2024

Research funding programme for International Communication
Austrian Research Association (Österreichische Forschungsgemeinschaf)
For the participation at the Text2Story Workshop at ECIR’24.

Travel grant for scientists (Reisekostenzuschuss für WissenschafterInnen)
Office of the Styrian Government (Amt der Steiermärkischen Landesregierung)
For the participation at CHIIR’24.

2023

The Framing of the Climate Debate: Computational Framing Analysis using Abstract Meaning Representation.
TU Graz: Initial funding program, 18th call.
As part of the consortium. Funding for 1 student assistant.

Erasmus+ Staff Mobility for Training
Host Institution: Bulgarian Academy of Sciences
For the 2nd Summer school on Deep Learning in Natural Language Processing 2023.

Travel grant for scientists (Reisekostenzuschuss für WissenschafterInnen)
Office of the Styrian Government (Amt der Steiermärkischen Landesregierung)
For the participation in symposium at The Web Conference 2023.

Program Committee/Reviewer

2025 ICWSM’25 (Jan.), ICWSM’26 (May, and September Cycle) Royal Society Open Science, RecSys’25 (long, short, and LBR), JMIR (Infodemiology and Infoveillance), JMIR Infodemiology (Reviews in Infodemiology), UMAP’25 HyPer workshop, TheWebConf’26 (UMAP track), Social Science Computer Review

2024 SIGIR’24 (Short papers), RecSys’24 (Long + Short), ICWSM’25 (Sep. Cycle), CSCW’25, TheWebConf’25

2023 ACL’23, SIGIR’23 (Full + Short papers), SemEval’23 (Task 3), RecSys’23 (Long + Short), EMNLP’23, Frontiers in Big Data (Recommender Systems - Reviews in Recommender Systems: 2022), WSDM’24, TheWebConf’24 UMAP track

2022 SIGIR’22 Long papers, RecSys’22 Main, EMNLP’22, WSDM’23, TheWebConf’23 UMAP track (among Best Reviewers)

2021 IUI’22 Main, IUI’22 Posters, RecSys’21 Main, RecSys’21 LBR, TheWebConf’22 WMCA track, SSCR

2020 IUI’21

Conference Talks and Attendence

2025

Presentation @ NetSci’25

Lightning Talk + Poster @ ASAI’25 Networking Event

Lightning Talk + Poster @ INRA’25 workshop (RecSys’25)

Lightning Talk @ Bilateral AI Retreat

2024

Workshop @ ECIR’24 - Presentation in the Text2Story’24 workshop

Workshop @ IUI’24 - Presentation in the Joint Workshop of HUMANIZE’24 and SOCIALIZE’24

Demo @ CHIIR’24 - Presentation and Demonstration of the FrameFinder Tool

Workshop @ WSDM’24 - Presentation in the Psychology-informed Information Access Systems Workshop (PsyIAS)

2023

Attendee @ RANLP’23 - Write-Up on LLMs

Session Chair @ TheWebConf’23 - User Modeling and Personalization: Privacy Preserving Recommendation, Contrastive Learning & Web Accessibility

Presenter @ TheWebConf’23 - PhD Symposium: Exploration of Framing Biases in Polarized Online Content Consumption

2022

Poster @ GraML - Opening Event (2022)

Poster @ ACSD’22 - Computational Framing Analysis in Online Media

Session Chair @ TheWebConf’22 - Web Mining and Content Analysis: Social 2

Attendee @ CHIIR’22

2021

Poster @ RecSys’21 - Predicting music relistening behavior using the ACT-R framework

Poster @ IC2S2’21 - Opinion Polarization on COVID-19 Measures: Integrating Surveys and Social Media Data

Poster @ ICWSM’21 - Studying Moral-based Differences in the Framing of Political Tweets

2020

Industry Talk @ RecSys’20 - On the Heterogeneous Information Needs in the Job Domain: A Unified Platform for Student Career

Workshop @ SocInfo’20 - Bridging the gap of polarization in public opinion on misinformed topics