About Me

I am a research fellow at the AI Center of ETH Zurich (Switzerland).

Prior to that, I was a research associate and doctoral student in the group for Data Analysis and Visualization at the University of Konstanz (Germany) and in the Visualization for Information Analysis lab at the OntarioTech University (Canada).

I work at the intersection of data analysis, visualization, computational linguistics, and explainable artificial intelligence. My research interest is in combining data mining and machine learning techniques with visual analytics, specifically for text data.



Mennatallah El-Assady


Data Analysis and Visualization

ETH AI Center (CH)



Developing Explainable and Interactive Machine Learning. https://explainer.ai/


Integrating Computational Linguistics and Visual Analytics. https://lingvis.io/


Analyzing Successful Rhetoric and Argumentation in Debates. http://visargue.uni.kn/

Visual Musicology

Exploring the Intersection of Musicology and Visual Analytics. https://visual-musicology.com/


Investigating Deliberation in Political Debates. https://valida.lingvis.io/


& Co-Organized Events


COMMA Workshop on Argument Visualization. https://argvis-workshop.lingvis.io/


IEEE VIS Workshop on Visualization for the Digital Humanities. http://vis4dh.org/


Workshop on Visualization as Added Value in the Development, Use, and Evaluation of Language Resources. http://tiny.cc/vislr


IEEE VIS Workshop on Visualization for AI Explainability. http://visxai.io/

Recent Publications

Augmenting Digital Sheet Music through Visual Analytics

Augmenting Digital Sheet Music through Visual Analytics

Music analysis tasks, such as structure identification and modulation detection, are tedious when performed manually due to the complexity of the common music notation (CMN). Fully automated analysis instead misses human intuition about relevance. Existing approaches use abstract data-driven visualizations to assist music analysis but lack a suitable connection to the CMN. Therefore, music analysts often prefer to remain in their familiar context. Our approach enhances the traditional analysis workflow by complementing CMN with interactive visualization entities as minimally intrusive augmentations. Gradual step-wise transitions empower analysts to retrace and comprehend the relationship between the CMN and abstract data representations. We leverage glyph-based visualizations for harmony, rhythm and melody to demonstrate our technique’s applicability. Designdriven visual query filters enable analysts to investigate statistical and semantic patterns on various abstraction levels. We conducted pair analytics sessions with 16 participants of different proficiency levels to gather qualitative feedback about the intuitiveness, traceability and understandability of our approach. The results show that MusicVis supports music analysts in getting new insights about feature characteristics while increasing their engagement and willingness to explore.

Quickly discover relevant content by filtering publications.