WebProfiler: User interaction prediction framework for web applications

Minwoo Joo, Wonjun Lee

Research output: Contribution to journalArticle

Abstract

User interaction prediction for Web applications is crucial to improve browsing experience. With the prediction, for instance, a browser can prefetch the content to be accessed next reducing long wait times in advance. However, predicting the user interaction is challenging in practice. Collecting detailed interaction data is difficult due to the constraints on target application and platform. Moreover, Web navigation prediction mechanisms for general applications have a low accuracy with conventional machine learning models. To this end, in this paper, we propose a Web interaction profiling framework, WebProfiler, which collects user interaction data in a generic way and accurately predicts the next navigation. Both navigation and click events are collected by using JavaScript event handlers and clicked objects are identified reliably through a document object model based approach. Furthermore, we adopt gated recurrent unit (GRU), a representative deep learning technique suitable for coping with time series Web interaction data, and present two advanced techniques for training the GRU-based model: Uniform resource locator (URL) grouping to handle the variant URLs of a Web page and Web embedding to represent both events in a unified vector space. The experimental results based on the real user interaction data showed that click events within an application improved the overall prediction performance by 13.7% on average, which were overlooked by most of the previous research. In addition, WebProfiler achieved an average F-measure of 0.798 for top three candidates where URL grouping and Web embedding contributed to 52.4% of the performance improvement.

Original languageEnglish
Article number8880603
Pages (from-to)154946-154958
Number of pages13
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Websites
Navigation
World Wide Web
Vector spaces
Learning systems
Time series

Keywords

  • Deep learning
  • gated recurrent unit (GRU)
  • navigation prediction
  • user interaction
  • web applications

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

WebProfiler : User interaction prediction framework for web applications. / Joo, Minwoo; Lee, Wonjun.

In: IEEE Access, Vol. 7, 8880603, 01.01.2019, p. 154946-154958.

Research output: Contribution to journalArticle

@article{14151bbba94d41ad8508cecf70473f7e,
title = "WebProfiler: User interaction prediction framework for web applications",
abstract = "User interaction prediction for Web applications is crucial to improve browsing experience. With the prediction, for instance, a browser can prefetch the content to be accessed next reducing long wait times in advance. However, predicting the user interaction is challenging in practice. Collecting detailed interaction data is difficult due to the constraints on target application and platform. Moreover, Web navigation prediction mechanisms for general applications have a low accuracy with conventional machine learning models. To this end, in this paper, we propose a Web interaction profiling framework, WebProfiler, which collects user interaction data in a generic way and accurately predicts the next navigation. Both navigation and click events are collected by using JavaScript event handlers and clicked objects are identified reliably through a document object model based approach. Furthermore, we adopt gated recurrent unit (GRU), a representative deep learning technique suitable for coping with time series Web interaction data, and present two advanced techniques for training the GRU-based model: Uniform resource locator (URL) grouping to handle the variant URLs of a Web page and Web embedding to represent both events in a unified vector space. The experimental results based on the real user interaction data showed that click events within an application improved the overall prediction performance by 13.7{\%} on average, which were overlooked by most of the previous research. In addition, WebProfiler achieved an average F-measure of 0.798 for top three candidates where URL grouping and Web embedding contributed to 52.4{\%} of the performance improvement.",
keywords = "Deep learning, gated recurrent unit (GRU), navigation prediction, user interaction, web applications",
author = "Minwoo Joo and Wonjun Lee",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2949077",
language = "English",
volume = "7",
pages = "154946--154958",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - WebProfiler

T2 - User interaction prediction framework for web applications

AU - Joo, Minwoo

AU - Lee, Wonjun

PY - 2019/1/1

Y1 - 2019/1/1

N2 - User interaction prediction for Web applications is crucial to improve browsing experience. With the prediction, for instance, a browser can prefetch the content to be accessed next reducing long wait times in advance. However, predicting the user interaction is challenging in practice. Collecting detailed interaction data is difficult due to the constraints on target application and platform. Moreover, Web navigation prediction mechanisms for general applications have a low accuracy with conventional machine learning models. To this end, in this paper, we propose a Web interaction profiling framework, WebProfiler, which collects user interaction data in a generic way and accurately predicts the next navigation. Both navigation and click events are collected by using JavaScript event handlers and clicked objects are identified reliably through a document object model based approach. Furthermore, we adopt gated recurrent unit (GRU), a representative deep learning technique suitable for coping with time series Web interaction data, and present two advanced techniques for training the GRU-based model: Uniform resource locator (URL) grouping to handle the variant URLs of a Web page and Web embedding to represent both events in a unified vector space. The experimental results based on the real user interaction data showed that click events within an application improved the overall prediction performance by 13.7% on average, which were overlooked by most of the previous research. In addition, WebProfiler achieved an average F-measure of 0.798 for top three candidates where URL grouping and Web embedding contributed to 52.4% of the performance improvement.

AB - User interaction prediction for Web applications is crucial to improve browsing experience. With the prediction, for instance, a browser can prefetch the content to be accessed next reducing long wait times in advance. However, predicting the user interaction is challenging in practice. Collecting detailed interaction data is difficult due to the constraints on target application and platform. Moreover, Web navigation prediction mechanisms for general applications have a low accuracy with conventional machine learning models. To this end, in this paper, we propose a Web interaction profiling framework, WebProfiler, which collects user interaction data in a generic way and accurately predicts the next navigation. Both navigation and click events are collected by using JavaScript event handlers and clicked objects are identified reliably through a document object model based approach. Furthermore, we adopt gated recurrent unit (GRU), a representative deep learning technique suitable for coping with time series Web interaction data, and present two advanced techniques for training the GRU-based model: Uniform resource locator (URL) grouping to handle the variant URLs of a Web page and Web embedding to represent both events in a unified vector space. The experimental results based on the real user interaction data showed that click events within an application improved the overall prediction performance by 13.7% on average, which were overlooked by most of the previous research. In addition, WebProfiler achieved an average F-measure of 0.798 for top three candidates where URL grouping and Web embedding contributed to 52.4% of the performance improvement.

KW - Deep learning

KW - gated recurrent unit (GRU)

KW - navigation prediction

KW - user interaction

KW - web applications

UR - http://www.scopus.com/inward/record.url?scp=85077954774&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077954774&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2949077

DO - 10.1109/ACCESS.2019.2949077

M3 - Article

AN - SCOPUS:85077954774

VL - 7

SP - 154946

EP - 154958

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8880603

ER -