Click sequence prediction in android mobile applications

Seokjun Lee, Rhan Ha, Hojung Cha

Research output: Contribution to journalArticle

Abstract

Predicting a click sequence in mobile applications improves the user experience in various ways. By predicting which button will be clicked next, one can predict how the application will work and how the device will operate. However, predicting the click sequence is difficult because of the problems involved in collecting click sequences in real application usage. More importantly, accurate predictions are extremely challenging. In this paper, we address these issues. We propose PathFinder, a scheme for collecting click events and based on them predicting the next click in the application. The clicks are collected with the Android Accessibility Service and the next click is predicted via long short-term memory (LSTM). For the prediction, the base click sequence model is first generated from all users' data; then, a personalized model is trained with an individual click sequence. As training data considerably influences the performance of LSTM, several techniques are developed to enhance the quality of the training data. The experimental results for 100 popular applications showed that the coverage and accuracy of click sequence tracing were 95% and 96%, respectively. Furthermore, PathFinder predicted the top three buttons that would be clicked next with a 0.76 F-measure for 1 775 043 real click data.

Original languageEnglish
Article number8470114
Pages (from-to)278-289
Number of pages12
JournalIEEE Transactions on Human-Machine Systems
Volume49
Issue number3
DOIs
Publication statusPublished - 2019 Jun 1

Fingerprint

coverage
event
performance
experience
Long short-term memory

All Science Journal Classification (ASJC) codes

  • Human Factors and Ergonomics
  • Control and Systems Engineering
  • Signal Processing
  • Human-Computer Interaction
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

@article{3f5152e7974047be8c5104c9dd302112,
title = "Click sequence prediction in android mobile applications",
abstract = "Predicting a click sequence in mobile applications improves the user experience in various ways. By predicting which button will be clicked next, one can predict how the application will work and how the device will operate. However, predicting the click sequence is difficult because of the problems involved in collecting click sequences in real application usage. More importantly, accurate predictions are extremely challenging. In this paper, we address these issues. We propose PathFinder, a scheme for collecting click events and based on them predicting the next click in the application. The clicks are collected with the Android Accessibility Service and the next click is predicted via long short-term memory (LSTM). For the prediction, the base click sequence model is first generated from all users' data; then, a personalized model is trained with an individual click sequence. As training data considerably influences the performance of LSTM, several techniques are developed to enhance the quality of the training data. The experimental results for 100 popular applications showed that the coverage and accuracy of click sequence tracing were 95{\%} and 96{\%}, respectively. Furthermore, PathFinder predicted the top three buttons that would be clicked next with a 0.76 F-measure for 1 775 043 real click data.",
author = "Seokjun Lee and Rhan Ha and Hojung Cha",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/THMS.2018.2868806",
language = "English",
volume = "49",
pages = "278--289",
journal = "IEEE Transactions on Human-Machine Systems",
issn = "2168-2291",
publisher = "IEEE Systems, Man, and Cybernetics Society",
number = "3",

}

Click sequence prediction in android mobile applications. / Lee, Seokjun; Ha, Rhan; Cha, Hojung.

In: IEEE Transactions on Human-Machine Systems, Vol. 49, No. 3, 8470114, 01.06.2019, p. 278-289.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Click sequence prediction in android mobile applications

AU - Lee, Seokjun

AU - Ha, Rhan

AU - Cha, Hojung

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Predicting a click sequence in mobile applications improves the user experience in various ways. By predicting which button will be clicked next, one can predict how the application will work and how the device will operate. However, predicting the click sequence is difficult because of the problems involved in collecting click sequences in real application usage. More importantly, accurate predictions are extremely challenging. In this paper, we address these issues. We propose PathFinder, a scheme for collecting click events and based on them predicting the next click in the application. The clicks are collected with the Android Accessibility Service and the next click is predicted via long short-term memory (LSTM). For the prediction, the base click sequence model is first generated from all users' data; then, a personalized model is trained with an individual click sequence. As training data considerably influences the performance of LSTM, several techniques are developed to enhance the quality of the training data. The experimental results for 100 popular applications showed that the coverage and accuracy of click sequence tracing were 95% and 96%, respectively. Furthermore, PathFinder predicted the top three buttons that would be clicked next with a 0.76 F-measure for 1 775 043 real click data.

AB - Predicting a click sequence in mobile applications improves the user experience in various ways. By predicting which button will be clicked next, one can predict how the application will work and how the device will operate. However, predicting the click sequence is difficult because of the problems involved in collecting click sequences in real application usage. More importantly, accurate predictions are extremely challenging. In this paper, we address these issues. We propose PathFinder, a scheme for collecting click events and based on them predicting the next click in the application. The clicks are collected with the Android Accessibility Service and the next click is predicted via long short-term memory (LSTM). For the prediction, the base click sequence model is first generated from all users' data; then, a personalized model is trained with an individual click sequence. As training data considerably influences the performance of LSTM, several techniques are developed to enhance the quality of the training data. The experimental results for 100 popular applications showed that the coverage and accuracy of click sequence tracing were 95% and 96%, respectively. Furthermore, PathFinder predicted the top three buttons that would be clicked next with a 0.76 F-measure for 1 775 043 real click data.

UR - http://www.scopus.com/inward/record.url?scp=85054369273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054369273&partnerID=8YFLogxK

U2 - 10.1109/THMS.2018.2868806

DO - 10.1109/THMS.2018.2868806

M3 - Article

VL - 49

SP - 278

EP - 289

JO - IEEE Transactions on Human-Machine Systems

JF - IEEE Transactions on Human-Machine Systems

SN - 2168-2291

IS - 3

M1 - 8470114

ER -