the BR method is limited by its strong assumption of
independent labels.
While we have discussed different approaches to
multi-label learning, the main contribution of this
work is not the technical approach applied, but rather
we draw attention to the critical human-centric issues
affecting the users’ experience of software applica-
tions, and the use of app reviews as a valuable proxy
to detect these issues.
8 CONCLUSION
This paper presents AH-CID, a novel tool that has the
means of detecting and analysing human-centric is-
sues in text, to allow developers to ascertain which
issues are adversely affecting their diverse user base.
Using a machine learning approach, a model was con-
structed and deployed with 91.4% accuracy and a
2.1% hamming loss. Also, the training data was bal-
anced resulting in a moderate-high F1 score.
In the future, we plan to investigate a larger set of
apps reviews and human-centric issues using our tool.
Additionally, an empirical study with users on their
perception of human-centric issues is another area for
our future work. We also plan to extend the tool and
add a user review feature for the end-users to use the
tool and detect HCIs in different apps to be able to se-
lect and download apps more wisely, from a human-
centric aspect.
ACKNOWLEDGEMENTS
Support for this work from ARC Laureate Program
FL190100035 and ARC Discovery DP200100020 is
gratefully acknowledged.
REFERENCES
Alshayban, A., Ahmed, I., and Malek, S. (2020). Acces-
sibility issues in android apps: State of affairs, sen-
timents, and ways forward. In Proceedings of the
ACM/IEEE 42nd International Conf. on Software En-
gineering, ICSE ’20, page 1323–1334, New York,
USA. Association for Computing Machinery.
AustralianGovernment (2020). Background to covidsafe. In
https://covidsafe.gov.au/background.html.
Belyakov, S., Bozhenyuk, A., Kacprzyk, J., and Rozenberg,
I. (2020). Intelligent planning of spatial analysis pro-
cess based on contexts. In International Conf. on In-
telligent and Fuzzy Systems, pages 10–17. Springer.
Carre
˜
no, L. V. G. and Winbladh, K. (2013). Analysis of
user comments: An approach for software require-
ments evolution. In ICSE.
Cherman, E. A., Monard, M. C., and Metz, J. (2011). Multi-
label problem transformation methods: a case study.
CLEI Electronic Journal, 14(1):4–4.
Di Sorbo, A., Panichella, S., Alexandru, C. V., Shima-
gaki, J., Visaggio, C. A., Canfora, G., and Gall,
H. C. (2016). What would users change in my app?
summarizing app reviews for recommending software
changes. In FSE.
Farooqui, T., Rana, T., and Jafari, F. (2019). Impact of
human-centered design process (hcdp) on software
development process. In 2019 2nd International Conf.
on Communication, Computing and Digital systems
(C-CODE), pages 110–114. IEEE.
GooglePlay (2020). Firefox browser: fast, private & safe
web browser - google play.
Grundy, J., Khalajzadeh, H., and Mcintosh, J. (2020). To-
wards human-centric model-driven software engineer-
ing. In ENASE, pages 229–238.
Grundy, J., Khalajzadeh, H., McIntosh, J., Kanij, T., and
Mueller, I. (2021). Humanise: Approaches to achieve
more human-centric software engineering. In Eval-
uation of Novel Approaches to Software Engineering:
15th International Conf., ENASE 2020, Prague, Czech
Republic, May 5–6, 2020, Revised Selected Papers 15,
pages 444–468. Springer International Publishing.
Hartzel, K. (2003). How self-efficacy and gender issues
affect software adoption and use. Communications of
the ACM, 46(9):167–171.
Jack, A. I., Dawson, A. J., Begany, K. L., Leckie, R. L.,
Barry, K. P., Ciccia, A. H., and Snyder, A. Z. (2013).
fmri reveals reciprocal inhibition between social and
physical cognitive domains. NeuroImage, 66:385–
401.
Levy, M. and Hadar, I. (2018). The importance of empathy
for analyzing privacy requirements. In 2018 IEEE 5th
International Workshop on Evolving Security & Pri-
vacy Requirements Engineering (ESPRE), pages 9–
13. IEEE.
Li, H., Zhang, L., Zhang, L., and Shen, J. (2010). A user
satisfaction analysis approach for software evolution.
In PIC, volume 2.
Maalej, W. and Nabil, H. (2015). Bug report, feature re-
quest, or simply praise? on automatically classifying
app reviews. In RE.
Madjarov, G., Kocev, D., Gjorgjevikj, D., and D
ˇ
zeroski,
S. (2012). An extensive experimental comparison of
methods for multi-label learning. Pattern recognition,
45(9):3084–3104.
Mao, J.-Y., Vredenburg, K., Smith, P. W., and Carey, T.
(2005). The state of user-centered design practice.
Communications of the ACM, 48(3):105–109.
Mathews, C., Ye, K., Grozdanovski, J., Marinelli, M.,
Zhong, K., Khalajzadeh, H., Obie, H., and Grundy,
J. (2021). AH-CID: A Tool to Automatically Detect
Human- Centric Issues in App Reviews [Data set].
https://doi.org/10.5281/zenodo.4475066.
Miller, T., Pedell, S., Lopez-Lorca, A. A., Mendoza, A.,
Sterling, L., and Keirnan, A. (2015). Emotion-led
ICSOFT 2021 - 16th International Conference on Software Technologies
396