Computing trust levels based on user's personality and observed system trustworthiness

Michaelis Kanakis; Shenja van der Graaf; Kostas Kalogiros; Wim Vanobberghen

doi:10.1007/978-3-319-22846-4_5

Computing trust levels based on user's personality and observed system trustworthiness

Michaelis Kanakis, Shenja van der Graaf, Kostas Kalogiros, Wim Vanobberghen

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

3 Citations (Scopus)

Abstract

In this article, we describe an approach for computing the current trust level of individual users towards an online system and present initial validation results from a small-scale experiment. This trust computational model relies upon survey research for identifying the set of key trust attributes and grouping users into four segments of expected behaviors. Each user’s initial trust level is computed based on a set of assumptions tailored to the specific segment she belongs to, while the trust level evolution takes additionally into account the system outcomes she has experienced so far. More specifically, the trust update follows a machine learning approach, where during the training phase that consists of a small number of system outcomes, users are asked to report their actual trust levels. Finally, we demonstrate the trustors’ segmentation validity and trust estimation accuracy by performing a small-scale experiment in the context of a fictitious online security service.

Original language	English
Title of host publication	Trust and Trustworthy Computing
Subtitle of host publication	8th International Conference, TRUST 2015, Heraklion, Greece, August 24-26, 2015, Proceedings
Editors	Mauro Conti, Matthias Schunter, Ioannis Askoxylakis
Place of Publication	Cham
Publisher	Springer
Pages	71-87
ISBN (Electronic)	978-3-319-22846-4
ISBN (Print)	978-3-319-22845-7
DOIs	https://doi.org/10.1007/978-3-319-22846-4_5
Publication status	Published - 6 Feb 2015
Externally published	Yes
Event	8th International Conference on Trust and Trustworthy Computing, TRUST 2015 - Heraklion, Greece Duration: 24 Aug 2015 → 26 Aug 2015 Conference number: 8

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	9229
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	8th International Conference on Trust and Trustworthy Computing, TRUST 2015
Abbreviated title	TRUST 2015
Country/Territory	Greece
City	Heraklion
Period	24/08/15 → 26/08/15

Keywords

n/a OA procedure

Access to Document

10.1007/978-3-319-22846-4_5

Cite this

Kanakis, M., van der Graaf, S., Kalogiros, K., & Vanobberghen, W. (2015). Computing trust levels based on user's personality and observed system trustworthiness. In M. Conti, M. Schunter, & I. Askoxylakis (Eds.), Trust and Trustworthy Computing: 8th International Conference, TRUST 2015, Heraklion, Greece, August 24-26, 2015, Proceedings (pp. 71-87). (Lecture Notes in Computer Science; Vol. 9229). Springer. https://doi.org/10.1007/978-3-319-22846-4_5

Kanakis, Michaelis ; van der Graaf, Shenja ; Kalogiros, Kostas et al. / Computing trust levels based on user's personality and observed system trustworthiness. Trust and Trustworthy Computing: 8th International Conference, TRUST 2015, Heraklion, Greece, August 24-26, 2015, Proceedings. editor / Mauro Conti ; Matthias Schunter ; Ioannis Askoxylakis. Cham : Springer, 2015. pp. 71-87 (Lecture Notes in Computer Science).

@inproceedings{6705e77f5b7941e89a374605714cdea1,

title = "Computing trust levels based on user's personality and observed system trustworthiness",

abstract = "In this article, we describe an approach for computing the current trust level of individual users towards an online system and present initial validation results from a small-scale experiment. This trust computational model relies upon survey research for identifying the set of key trust attributes and grouping users into four segments of expected behaviors. Each user{\textquoteright}s initial trust level is computed based on a set of assumptions tailored to the specific segment she belongs to, while the trust level evolution takes additionally into account the system outcomes she has experienced so far. More specifically, the trust update follows a machine learning approach, where during the training phase that consists of a small number of system outcomes, users are asked to report their actual trust levels. Finally, we demonstrate the trustors{\textquoteright} segmentation validity and trust estimation accuracy by performing a small-scale experiment in the context of a fictitious online security service.",

keywords = "n/a OA procedure",

author = "Michaelis Kanakis and {van der Graaf}, Shenja and Kostas Kalogiros and Wim Vanobberghen",

year = "2015",

month = feb,

day = "6",

doi = "10.1007/978-3-319-22846-4_5",

language = "English",

isbn = "978-3-319-22845-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "71--87",

editor = "Mauro Conti and Matthias Schunter and Ioannis Askoxylakis",

booktitle = "Trust and Trustworthy Computing",

address = "Germany",

note = "8th International Conference on Trust and Trustworthy Computing, TRUST 2015, TRUST 2015 ; Conference date: 24-08-2015 Through 26-08-2015",

}

Kanakis, M, van der Graaf, S, Kalogiros, K & Vanobberghen, W 2015, Computing trust levels based on user's personality and observed system trustworthiness. in M Conti, M Schunter & I Askoxylakis (eds), Trust and Trustworthy Computing: 8th International Conference, TRUST 2015, Heraklion, Greece, August 24-26, 2015, Proceedings. Lecture Notes in Computer Science, vol. 9229, Springer, Cham, pp. 71-87, 8th International Conference on Trust and Trustworthy Computing, TRUST 2015, Heraklion, Greece, 24/08/15. https://doi.org/10.1007/978-3-319-22846-4_5

Computing trust levels based on user's personality and observed system trustworthiness. / Kanakis, Michaelis; van der Graaf, Shenja; Kalogiros, Kostas et al.
Trust and Trustworthy Computing: 8th International Conference, TRUST 2015, Heraklion, Greece, August 24-26, 2015, Proceedings. ed. / Mauro Conti; Matthias Schunter; Ioannis Askoxylakis. Cham: Springer, 2015. p. 71-87 (Lecture Notes in Computer Science; Vol. 9229).

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

TY - GEN

T1 - Computing trust levels based on user's personality and observed system trustworthiness

AU - Kanakis, Michaelis

AU - van der Graaf, Shenja

AU - Kalogiros, Kostas

AU - Vanobberghen, Wim

N1 - Conference code: 8

PY - 2015/2/6

Y1 - 2015/2/6

N2 - In this article, we describe an approach for computing the current trust level of individual users towards an online system and present initial validation results from a small-scale experiment. This trust computational model relies upon survey research for identifying the set of key trust attributes and grouping users into four segments of expected behaviors. Each user’s initial trust level is computed based on a set of assumptions tailored to the specific segment she belongs to, while the trust level evolution takes additionally into account the system outcomes she has experienced so far. More specifically, the trust update follows a machine learning approach, where during the training phase that consists of a small number of system outcomes, users are asked to report their actual trust levels. Finally, we demonstrate the trustors’ segmentation validity and trust estimation accuracy by performing a small-scale experiment in the context of a fictitious online security service.

AB - In this article, we describe an approach for computing the current trust level of individual users towards an online system and present initial validation results from a small-scale experiment. This trust computational model relies upon survey research for identifying the set of key trust attributes and grouping users into four segments of expected behaviors. Each user’s initial trust level is computed based on a set of assumptions tailored to the specific segment she belongs to, while the trust level evolution takes additionally into account the system outcomes she has experienced so far. More specifically, the trust update follows a machine learning approach, where during the training phase that consists of a small number of system outcomes, users are asked to report their actual trust levels. Finally, we demonstrate the trustors’ segmentation validity and trust estimation accuracy by performing a small-scale experiment in the context of a fictitious online security service.

KW - n/a OA procedure

UR - https://cris.vub.be/en/publications/computing-trust-levels-based-on-users-personality-and-observed-system-trustworthiness(50ebbd4e-27aa-41ba-97b9-5d198420adce).html

U2 - 10.1007/978-3-319-22846-4_5

DO - 10.1007/978-3-319-22846-4_5

M3 - Conference contribution

SN - 978-3-319-22845-7

T3 - Lecture Notes in Computer Science

SP - 71

EP - 87

BT - Trust and Trustworthy Computing

A2 - Conti, Mauro

A2 - Schunter, Matthias

A2 - Askoxylakis, Ioannis

PB - Springer

CY - Cham

T2 - 8th International Conference on Trust and Trustworthy Computing, TRUST 2015

Y2 - 24 August 2015 through 26 August 2015

ER -

Kanakis M, van der Graaf S, Kalogiros K, Vanobberghen W. Computing trust levels based on user's personality and observed system trustworthiness. In Conti M, Schunter M, Askoxylakis I, editors, Trust and Trustworthy Computing: 8th International Conference, TRUST 2015, Heraklion, Greece, August 24-26, 2015, Proceedings. Cham: Springer. 2015. p. 71-87. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-22846-4_5

Computing trust levels based on user's personality and observed system trustworthiness

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this