PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry

Xin Yi; Chen Wang; Xiaojun Bi; Yuanchun Shi

doi:10.1145/3313831.3376441

PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry

Xin Yi
, Chen Wang
, Xiaojun Bi
, Yuanchun Shi

Computer Science

Ministry of Education of the People's Republic of China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

We investigated how to incorporate implicit touch pressure, finger pressure applied to a touch surface during typing, to improve text entry performance via statistical decoding. We focused on one-handed touch-typing on indirect interface as an example scenario. We first collected typing data on a pressure-sensitive touchpad, and analyzed users' typing behavior such as touch point distribution, key-to-finger mappings, and pressure images. Our investigation revealed distinct pressure patterns for different keys. Based on the findings, we performed a series of simulations to iteratively optimize the statistical decoding algorithm. Our investigation led to a Markov-Bayesian decoder incorporating pressure image data into decoding. It improved the top-1 accuracy from 53% to 74% over a naive Bayesian decoder. We then implemented PalmBoard, a text entry method that implemented the Markov-Bayesian decoder and effectively supported one-handed touch-typing on indirect interfaces. A user study showed participants achieved an average speed of 32.8 WPM with 0.6% error rate. Expert typists could achieve 40.2 WPM with 30 minutes of practice. Overall, our investigation showed that incorporating implicit touch pressure is effective in improving text entry decoding.

Original language	English
Title of host publication	CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450367080
DOIs	https://doi.org/10.1145/3313831.3376441
State	Published - Apr 21 2020
Event	2020 ACM CHI Conference on Human Factors in Computing Systems, CHI 2020 - Honolulu, United States Duration: Apr 25 2020 → Apr 30 2020

Publication series

Name	Conference on Human Factors in Computing Systems - Proceedings

Conference

Conference	2020 ACM CHI Conference on Human Factors in Computing Systems, CHI 2020
Country/Territory	United States
City	Honolulu
Period	04/25/20 → 04/30/20

Keywords

input prediction
text entry
touch pressure
touch-typing

Access to Document

10.1145/3313831.3376441

Cite this

Yi, X., Wang, C., Bi, X., & Shi, Y. (2020). PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry. In CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems Article 3376441 (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3313831.3376441

@inproceedings{f699daf41f524a6b9b4ea18bb9a001ba,

title = "PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry",

abstract = "We investigated how to incorporate implicit touch pressure, finger pressure applied to a touch surface during typing, to improve text entry performance via statistical decoding. We focused on one-handed touch-typing on indirect interface as an example scenario. We first collected typing data on a pressure-sensitive touchpad, and analyzed users' typing behavior such as touch point distribution, key-to-finger mappings, and pressure images. Our investigation revealed distinct pressure patterns for different keys. Based on the findings, we performed a series of simulations to iteratively optimize the statistical decoding algorithm. Our investigation led to a Markov-Bayesian decoder incorporating pressure image data into decoding. It improved the top-1 accuracy from 53\% to 74\% over a naive Bayesian decoder. We then implemented PalmBoard, a text entry method that implemented the Markov-Bayesian decoder and effectively supported one-handed touch-typing on indirect interfaces. A user study showed participants achieved an average speed of 32.8 WPM with 0.6\% error rate. Expert typists could achieve 40.2 WPM with 30 minutes of practice. Overall, our investigation showed that incorporating implicit touch pressure is effective in improving text entry decoding.",

keywords = "input prediction, text entry, touch pressure, touch-typing",

author = "Xin Yi and Chen Wang and Xiaojun Bi and Yuanchun Shi",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 2020 ACM CHI Conference on Human Factors in Computing Systems, CHI 2020 ; Conference date: 25-04-2020 Through 30-04-2020",

year = "2020",

month = apr,

day = "21",

doi = "10.1145/3313831.3376441",

language = "English",

series = "Conference on Human Factors in Computing Systems - Proceedings",

publisher = "Association for Computing Machinery",

booktitle = "CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems",

}

Yi, X, Wang, C, Bi, X & Shi, Y 2020, PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry. in CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems., 3376441, Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, 2020 ACM CHI Conference on Human Factors in Computing Systems, CHI 2020, Honolulu, United States, 04/25/20. https://doi.org/10.1145/3313831.3376441

PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry. / Yi, Xin; Wang, Chen; Bi, Xiaojun et al.
CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2020. 3376441 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - PalmBoard

T2 - 2020 ACM CHI Conference on Human Factors in Computing Systems, CHI 2020

AU - Yi, Xin

AU - Wang, Chen

AU - Bi, Xiaojun

AU - Shi, Yuanchun

PY - 2020/4/21

Y1 - 2020/4/21

N2 - We investigated how to incorporate implicit touch pressure, finger pressure applied to a touch surface during typing, to improve text entry performance via statistical decoding. We focused on one-handed touch-typing on indirect interface as an example scenario. We first collected typing data on a pressure-sensitive touchpad, and analyzed users' typing behavior such as touch point distribution, key-to-finger mappings, and pressure images. Our investigation revealed distinct pressure patterns for different keys. Based on the findings, we performed a series of simulations to iteratively optimize the statistical decoding algorithm. Our investigation led to a Markov-Bayesian decoder incorporating pressure image data into decoding. It improved the top-1 accuracy from 53% to 74% over a naive Bayesian decoder. We then implemented PalmBoard, a text entry method that implemented the Markov-Bayesian decoder and effectively supported one-handed touch-typing on indirect interfaces. A user study showed participants achieved an average speed of 32.8 WPM with 0.6% error rate. Expert typists could achieve 40.2 WPM with 30 minutes of practice. Overall, our investigation showed that incorporating implicit touch pressure is effective in improving text entry decoding.

AB - We investigated how to incorporate implicit touch pressure, finger pressure applied to a touch surface during typing, to improve text entry performance via statistical decoding. We focused on one-handed touch-typing on indirect interface as an example scenario. We first collected typing data on a pressure-sensitive touchpad, and analyzed users' typing behavior such as touch point distribution, key-to-finger mappings, and pressure images. Our investigation revealed distinct pressure patterns for different keys. Based on the findings, we performed a series of simulations to iteratively optimize the statistical decoding algorithm. Our investigation led to a Markov-Bayesian decoder incorporating pressure image data into decoding. It improved the top-1 accuracy from 53% to 74% over a naive Bayesian decoder. We then implemented PalmBoard, a text entry method that implemented the Markov-Bayesian decoder and effectively supported one-handed touch-typing on indirect interfaces. A user study showed participants achieved an average speed of 32.8 WPM with 0.6% error rate. Expert typists could achieve 40.2 WPM with 30 minutes of practice. Overall, our investigation showed that incorporating implicit touch pressure is effective in improving text entry decoding.

KW - input prediction

KW - text entry

KW - touch pressure

KW - touch-typing

UR - https://www.scopus.com/pages/publications/85091320218

U2 - 10.1145/3313831.3376441

DO - 10.1145/3313831.3376441

M3 - Conference contribution

AN - SCOPUS:85091320218

T3 - Conference on Human Factors in Computing Systems - Proceedings

BT - CHI 2020 - Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

Y2 - 25 April 2020 through 30 April 2020

ER -

PalmBoard: Leveraging Implicit Touch Pressure in Statistical Decoding for Indirect Text Entry

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this