Study on Deep Learning Technical Debt

As software engineering research teams at the University of Sannio (Italy) and Università della Svizzera Italiana (USI) we are interested in assessing a catalogue of Self-Admitted Technical Debt (SATD) in ML-intensive systems, focusing more on the technical debt affecting the ML-specific code. The catalogue features 7 categories, concerning different kinds of problems.

For each question, you need to provide an answer indicating whether or not you agree on the relevance of the identified SATD. The answer will be provided by choosing an option in a 5-level scale (strongly agree, weakly agree, borderline, weakly disagree, strongly disagree), plus a “don’t know” option.

Filling out the survey will take about 5 minutes.

Please note that your identity and personal data will not be disclosed, while we plan to use the aggregated results and anonymized responses as part of a scientific publication.

If you have any questions about the questionnaire or our research, please do not hesitate to contact us.

Best Regards,

Federica Pepe (f.pepe8@studenti.unisannio.it)
Fiorella Zampetti (fzampetti@unisannio.it)
Antonio Mastropaolo (antonio.mastropaolo@usi.ch)
Gabriele Bavota (gabriele.bavota@usi.ch)
Massimiliano Di Penta (dipenta@unisannio.it)