The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers

被引：58

作者：

Buschek, Daniel ^{[1
]}

Zurn, Martin ^{[2
]}

Eiband, Malin ^{[2
]}

机构：

[1] Univ Bayreuth, Dept Comp Sci, Res Grp HCI AI, Bayreuth, Germany

[2] Ludwig Maximilians Univ Munchen, Munich, Germany

来源：

CHI '21: PROCEEDINGS OF THE 2021 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS | 2021年

关键词：

Text entry; typing; language model; text suggestions; deep learning; neural network; dataset;

D O I：

10.1145/3411764.3445372

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We present an in-depth analysis of the impact of multi-word suggestion choices from a neural language model on user behaviour regarding input and text composition in email writing. Our study for the first time compares different numbers of parallel suggestions, and use by native and non-native English writers, to explore a trade-off of "efficiency vs ideation", emerging from recent literature. We built a text editor prototype with a neural language model (GPT-2), refined in a prestudy with 30 people. In an online study (N=156), people composed emails in four conditions (0/1/3/6 parallel suggestions). Our results reveal (1) benefits for ideation, and costs for efficiency, when suggesting multiple phrases; (2) that non-native speakers benefit more from more suggestions; and (3) further insights into behaviour patterns. We discuss implications for research, the design of interactive suggestion systems, and the vision of supporting writers with AI instead of replacing them.

引用

页数：13

共 74 条

[1] Learning New Words and Spelling with Autocorrections [J].

Arif, Ahmed Sabbir ;

Sylla, Cristina ;

Mazalek, Ali .

PROCEEDINGS OF THE 2016 ACM INTERNATIONAL CONFERENCE ON INTERACTIVE SURFACES AND SPACES, (ISS 2016), 2016, :409-414

[2] Predictive Text Encourages Predictable Writing [J].

Arnold, Kenneth C. ;

Chauncey, Krysta ;

Gajos, Krzysztof Z. .

PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT USER INTERFACES, IUI 2020, 2020, :128-138

[3] On Suggesting Phrases vs. Predicting Words for Mobile Text Composition [J].

Arnold, Kenneth C. ;

Gajos, Krzysztof Z. ;

Kalai, Adam T. .

UIST 2016: PROCEEDINGS OF THE 29TH ANNUAL SYMPOSIUM ON USER INTERFACE SOFTWARE AND TECHNOLOGY, 2016, :603-608

[4]

Arnold Kenneth C., 2017, ARXIV171001799

[5]

Arnold Kenneth C., 2018, P 44 GRAPH INT C, P42, DOI DOI 10.20380/GI2018.07

[6] Model of Visual Search and Selection Time in Linear Menus [J].

Badly, Gilles ;

Oulasvirta, Antti ;

Brumby, Duncan P. ;

Howes, Andrew .

32ND ANNUAL ACM CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI 2014), 2014, :3865-3874

[7] The Limits of Expert Text Entry Speed on Mobile Keyboards with Autocorrect [J].

Banovic, Nikola ;

Sethapakdi, Ticha ;

Hari, Yasasvi ;

Dey, Anind K. ;

Mankoff, Jennifer .

PROCEEDINGS OF THE 21ST INTERNATIONAL CONFERENCE ON HUMAN-COMPUTER INTERACTION WITH MOBILE DEVICES AND SERVICES (MOBILEHCI'19), 2019,

[8]

Barber David, 2012, LEARNING

[9] Fitting Linear Mixed-Effects Models Using lme4 [J].

Bates, Douglas ;

Maechler, Martin ;

Bolker, Benjamin M. ;

Walker, Steven C. .

JOURNAL OF STATISTICAL SOFTWARE, 2015, 67 (01) :1-48

[10] Both Complete and Correct? Multi-Objective Optimization of Touchscreen Keyboard [J].

Bi, Xiaojun ;

Ouyang, Tom ;

Zhai, Shumin .

32ND ANNUAL ACM CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI 2014), 2014, :2297-2306

← 1 2 3 4 5 6 7 8 →