Show simple item record

dc.contributor.authorHooper, Mark Alanen
dc.date.accessioned2019-04-26T10:40:27Z
dc.date.available2019-04-26T10:40:27Z
dc.date.issued2018-12
dc.identifier.citationHooper, M.A. (2018) ‘Leveraging contextual-cognitive relationships into mobile commerce systems’. PhD thesis. University of Bedfordshire.en
dc.identifier.urihttp://hdl.handle.net/10547/623248
dc.descriptionA thesis submitted to the University of Bedfordshire in partial fulfilment of the requirements for the degree of Doctor of Philosophyen
dc.description.abstractMobile smart devices are becoming increasingly important within the on-line purchasing cycle. Thus the requirement for mobile commerce systems to become truly context-aware remains paramount if they are to be effective within the varied situations that mobile users encounter. Where traditionally a recommender system will focus upon the user – item relationship, i.e. what to recommend, in this thesis it is proposed that due to the complexity of mobile user situational profiles the how and when must also be considered for recommendations to be effective. Though non-trivial, it should be, through the understanding of a user’s ability to complete certain cognitive processes, possible to determine the likelihood of engagement and therefore the success of the recommendation. This research undertakes an investigation into physical and modal contexts and presents findings as to their relationships with cognitive processes. Through the introduction of the novel concept, disruptive contexts, situational contexts, including noise, distractions and user activity, are identified as having significant effects upon the relationship between user affective state and cognitive capability. Experimental results demonstrate that by understanding specific cognitive capabilities, e.g. a user’s perception of advert content and user levels of purchase-decision involvement, a system can determine potential user engagement and therefore improve the effectiveness of recommender systems’ performance. A quantitative approach is followed with a reliance upon statistical measures to inform the development, and subsequent validation, of a contextual-cognitive model that was implemented as part of a context-aware system. The development of SiDISense (Situational Decision Involvement Sensing system) demonstrated, through the use of smart-phone sensors and machine learning, that is was viable to classify subjectively rated contexts to then infer levels of cognitive capability and therefore likelihood of positive user engagement. Through this success in furthering the understanding of contextual-cognitive relationships there are novel and significant advances that are now viable within the area of m-commerce.
dc.language.isoenen
dc.publisherUniversity of Bedfordshireen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectcontext-awarenessen
dc.subjectcognitive relationshipsen
dc.subjectmobile commerceen
dc.subjectdisruptive contextsen
dc.subjectuser behaviouren
dc.subjectN240 Retail Managementen
dc.titleLeveraging contextual-cognitive relationships into mobile commerce systemsen
dc.typeThesis or dissertationen
dc.type.qualificationnamePhDen_GB
dc.type.qualificationlevelPhDen
dc.publisher.institutionUniversity of Bedfordshireen
html.description.abstractMobile smart devices are becoming increasingly important within the on-line purchasing cycle. Thus the requirement for mobile commerce systems to become truly context-aware remains paramount if they are to be effective within the varied situations that mobile users encounter. Where traditionally a recommender system will focus upon the user – item relationship, i.e. what to recommend, in this thesis it is proposed that due to the complexity of mobile user situational profiles the how and when must also be considered for recommendations to be effective. Though non-trivial, it should be, through the understanding of a user’s ability to complete certain cognitive processes, possible to determine the likelihood of engagement and therefore the success of the recommendation. This research undertakes an investigation into physical and modal contexts and presents findings as to their relationships with cognitive processes. Through the introduction of the novel concept, disruptive contexts, situational contexts, including noise, distractions and user activity, are identified as having significant effects upon the relationship between user affective state and cognitive capability. Experimental results demonstrate that by understanding specific cognitive capabilities, e.g. a user’s perception of advert content and user levels of purchase-decision involvement, a system can determine potential user engagement and therefore improve the effectiveness of recommender systems’ performance. A quantitative approach is followed with a reliance upon statistical measures to inform the development, and subsequent validation, of a contextual-cognitive model that was implemented as part of a context-aware system. The development of SiDISense (Situational Decision Involvement Sensing system) demonstrated, through the use of smart-phone sensors and machine learning, that is was viable to classify subjectively rated contexts to then infer levels of cognitive capability and therefore likelihood of positive user engagement. Through this success in furthering the understanding of contextual-cognitive relationships there are novel and significant advances that are now viable within the area of m-commerce.


Files in this item

Thumbnail
Name:
Leveraging contextual-cognitive ...
Size:
8.605Mb
Format:
PDF
Description:
Thesis

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by-nc-nd/4.0/
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc-nd/4.0/