EntityBot: Supporting everyday digital tasks with entity recommendations

Tung Vuong; Salvatore Andolina; Giulio Jacucci; Pedram Daee; Khalil Klouche; Mats Sjöberg; Tuukka Ruotsalo; Samuel Kaski

doi:10.1145/3460231.3478883

EntityBot: Supporting everyday digital tasks with entity recommendations

Tung Vuong, Salvatore Andolina, Giulio Jacucci, Pedram Daee, Khalil Klouche, Mats Sjöberg, Tuukka Ruotsalo, Samuel Kaski

Machine Learning

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

4 Citations (Scopus)

Abstract

Everyday digital tasks can highly benefit from systems that recommend the right information to use at the right time. However, existing solutions typically support only specific applications and tasks. In this demo, we showcase EntityBot, a system that captures context across application boundaries and recommends information entities related to the current task. The user's digital activity is continuously monitored by capturing all content on the computer screen using optical character recognition. This includes all applications and services being used and specific to individuals' computer usages such as instant messaging, emailing, web browsing, and word processing. A linear model is then applied to detect the user's task context to retrieve entities such as applications, documents, contact information, and several keywords determining the task. The system has been evaluated with real-world tasks, demonstrating that the recommendation had an impact on the tasks and led to high user satisfaction.

Original language	English
Title of host publication	RecSys 2021 - 15th ACM Conference on Recommender Systems
Number of pages	4
Publisher	Association for Computing Machinery, Inc.
Publication date	13 Sep 2021
Pages	753-756
ISBN (Electronic)	9781450384582
DOIs	https://doi.org/10.1145/3460231.3478883
Publication status	Published - 13 Sep 2021
Event	15th ACM Conference on Recommender Systems, RecSys 2021 - Virtual, Online, Netherlands Duration: 27 Sep 2021 → 1 Oct 2021

Conference

Conference	15th ACM Conference on Recommender Systems, RecSys 2021
Country/Territory	Netherlands
City	Virtual, Online
Period	27/09/2021 → 01/10/2021
Sponsor	ACM Special Interest Group on Artificial Intelligence (SIGAI), ACM Special Interest Group on Computer-Human Interaction (SIGCHI), ACM Special Interest Group on Hypertext, Hypermedia, and Web (ACM Special Interest Group on Hypertext, Hypermedia, and Web), ACM Special Interest Group on Information Retrieval (SIGIR), ACM Special Interest Group on Knowledge Discovery in Data (SIGKDD), Special Interest Group on Economics and Computation (SIGecom)

Series	RecSys 2021 - 15th ACM Conference on Recommender Systems

Bibliographical note

Funding Information:
Partially funded by the EU H2020 project CO-ADAPT, the MIUR (PON AIM), and the Academy of Finland (322653, 328875, 336085, 319264, 292334).

Publisher Copyright:
© 2021 Owner/Author.

Keywords

Proactive information retrieval
Real-world tasks
User intent modeling

Access to Document

10.1145/3460231.3478883

Cite this

Vuong, T., Andolina, S., Jacucci, G., Daee, P., Klouche, K., Sjöberg, M., Ruotsalo, T., & Kaski, S. (2021). EntityBot: Supporting everyday digital tasks with entity recommendations. In RecSys 2021 - 15th ACM Conference on Recommender Systems (pp. 753-756). Association for Computing Machinery, Inc.. RecSys 2021 - 15th ACM Conference on Recommender Systems https://doi.org/10.1145/3460231.3478883

EntityBot : Supporting everyday digital tasks with entity recommendations. / Vuong, Tung; Andolina, Salvatore; Jacucci, Giulio; Daee, Pedram; Klouche, Khalil; Sjöberg, Mats; Ruotsalo, Tuukka; Kaski, Samuel.

RecSys 2021 - 15th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc., 2021. p. 753-756 (RecSys 2021 - 15th ACM Conference on Recommender Systems).

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

Vuong, T, Andolina, S, Jacucci, G, Daee, P, Klouche, K, Sjöberg, M, Ruotsalo, T & Kaski, S 2021, EntityBot: Supporting everyday digital tasks with entity recommendations. in RecSys 2021 - 15th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc., RecSys 2021 - 15th ACM Conference on Recommender Systems, pp. 753-756, 15th ACM Conference on Recommender Systems, RecSys 2021, Virtual, Online, Netherlands, 27/09/2021. https://doi.org/10.1145/3460231.3478883

Vuong, Tung ; Andolina, Salvatore ; Jacucci, Giulio ; Daee, Pedram ; Klouche, Khalil ; Sjöberg, Mats ; Ruotsalo, Tuukka ; Kaski, Samuel. / EntityBot : Supporting everyday digital tasks with entity recommendations. RecSys 2021 - 15th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc., 2021. pp. 753-756 (RecSys 2021 - 15th ACM Conference on Recommender Systems).

@inproceedings{0271be36f9dc45598ca6e3afda5276d5,

title = "EntityBot: Supporting everyday digital tasks with entity recommendations",

abstract = "Everyday digital tasks can highly benefit from systems that recommend the right information to use at the right time. However, existing solutions typically support only specific applications and tasks. In this demo, we showcase EntityBot, a system that captures context across application boundaries and recommends information entities related to the current task. The user's digital activity is continuously monitored by capturing all content on the computer screen using optical character recognition. This includes all applications and services being used and specific to individuals' computer usages such as instant messaging, emailing, web browsing, and word processing. A linear model is then applied to detect the user's task context to retrieve entities such as applications, documents, contact information, and several keywords determining the task. The system has been evaluated with real-world tasks, demonstrating that the recommendation had an impact on the tasks and led to high user satisfaction. ",

keywords = "Proactive information retrieval, Real-world tasks, User intent modeling",

author = "Tung Vuong and Salvatore Andolina and Giulio Jacucci and Pedram Daee and Khalil Klouche and Mats Sj{\"o}berg and Tuukka Ruotsalo and Samuel Kaski",

note = "Funding Information: Partially funded by the EU H2020 project CO-ADAPT, the MIUR (PON AIM), and the Academy of Finland (322653, 328875, 336085, 319264, 292334). Publisher Copyright: {\textcopyright} 2021 Owner/Author.; 15th ACM Conference on Recommender Systems, RecSys 2021 ; Conference date: 27-09-2021 Through 01-10-2021",

year = "2021",

month = sep,

day = "13",

doi = "10.1145/3460231.3478883",

language = "English",

series = "RecSys 2021 - 15th ACM Conference on Recommender Systems",

pages = "753--756",

booktitle = "RecSys 2021 - 15th ACM Conference on Recommender Systems",

publisher = "Association for Computing Machinery, Inc.",

}

TY - GEN

T1 - EntityBot

T2 - 15th ACM Conference on Recommender Systems, RecSys 2021

AU - Vuong, Tung

AU - Andolina, Salvatore

AU - Jacucci, Giulio

AU - Daee, Pedram

AU - Klouche, Khalil

AU - Sjöberg, Mats

AU - Ruotsalo, Tuukka

AU - Kaski, Samuel

N1 - Funding Information: Partially funded by the EU H2020 project CO-ADAPT, the MIUR (PON AIM), and the Academy of Finland (322653, 328875, 336085, 319264, 292334). Publisher Copyright: © 2021 Owner/Author.

PY - 2021/9/13

Y1 - 2021/9/13

N2 - Everyday digital tasks can highly benefit from systems that recommend the right information to use at the right time. However, existing solutions typically support only specific applications and tasks. In this demo, we showcase EntityBot, a system that captures context across application boundaries and recommends information entities related to the current task. The user's digital activity is continuously monitored by capturing all content on the computer screen using optical character recognition. This includes all applications and services being used and specific to individuals' computer usages such as instant messaging, emailing, web browsing, and word processing. A linear model is then applied to detect the user's task context to retrieve entities such as applications, documents, contact information, and several keywords determining the task. The system has been evaluated with real-world tasks, demonstrating that the recommendation had an impact on the tasks and led to high user satisfaction.

AB - Everyday digital tasks can highly benefit from systems that recommend the right information to use at the right time. However, existing solutions typically support only specific applications and tasks. In this demo, we showcase EntityBot, a system that captures context across application boundaries and recommends information entities related to the current task. The user's digital activity is continuously monitored by capturing all content on the computer screen using optical character recognition. This includes all applications and services being used and specific to individuals' computer usages such as instant messaging, emailing, web browsing, and word processing. A linear model is then applied to detect the user's task context to retrieve entities such as applications, documents, contact information, and several keywords determining the task. The system has been evaluated with real-world tasks, demonstrating that the recommendation had an impact on the tasks and led to high user satisfaction.

KW - Proactive information retrieval

KW - Real-world tasks

KW - User intent modeling

U2 - 10.1145/3460231.3478883

DO - 10.1145/3460231.3478883

M3 - Article in proceedings

AN - SCOPUS:85115602643

T3 - RecSys 2021 - 15th ACM Conference on Recommender Systems

SP - 753

EP - 756

BT - RecSys 2021 - 15th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc.

Y2 - 27 September 2021 through 1 October 2021

ER -