Academia.eduAcademia.edu

Figure 17 – uploaded by Dana Al Qudah

See full PDFdownloadDownload figure
Figure 4.3: MyAds layered processing framework

Figure 4 3: MyAds layered processing framework

Related Figures (91)

Table 1.1: Mapping research problems to research questions and objectives
Table 1.1: Mapping research problems to research questions and objectives
Figure 2.2: Schubert and Leimstoll summery for personalised e-commerce applications [36]
Figure 2.2: Schubert and Leimstoll summery for personalised e-commerce applications [36]
Figure 2.3: Sicilia framework for personalisation of e-commerce [37] emphasises the importance of the approaches used.
Figure 2.3: Sicilia framework for personalisation of e-commerce [37] emphasises the importance of the approaches used.
Figure 2.5: AdRosa Overview Method for Adaptive Advertising [15]
Figure 2.5: AdRosa Overview Method for Adaptive Advertising [15]
deliver the proper advertisements, as shown below in Figure 2.6[41].
deliver the proper advertisements, as shown below in Figure 2.6[41].
Figure 2.7: Layered Architecture for Advertisements in On Demand TV [42] process within the platform.
Figure 2.7: Layered Architecture for Advertisements in On Demand TV [42] process within the platform.
Figure 2.8: Classical loop of User Modelling and Adaptation in Adaptive Systems by [19] illustrates the main blueprint for adaptive systems [19].
Figure 2.8: Classical loop of User Modelling and Adaptation in Adaptive Systems by [19] illustrates the main blueprint for adaptive systems [19].
Figure 2.9: Generic architecture of adaptive hypermedia systems [52] and 6.2.
Figure 2.9: Generic architecture of adaptive hypermedia systems [52] and 6.2.
Figure 2.10: Adaptive Hypermedia Techniques by Brusilovsky [19] annotating and map adaptation [19]. he direct guidance, adaptation of links sorting, adaptation of links hiding, adaption of links
Figure 2.10: Adaptive Hypermedia Techniques by Brusilovsky [19] annotating and map adaptation [19]. he direct guidance, adaptation of links sorting, adaptation of links hiding, adaption of links
Figure 2.11 : An Updated Taxonomy of Adaptation Techniques and Approaches[23] [22]
Figure 2.11 : An Updated Taxonomy of Adaptation Techniques and Approaches[23] [22]
There are a number of techniques to be used with users that are involved in an experiment, based
There are a number of techniques to be used with users that are involved in an experiment, based
Another thinking technique — slightly less frequently used, but quite useful and able to generate
Another thinking technique — slightly less frequently used, but quite useful and able to generate
Table 3.1: Different methodologies for human centric IS design, as described in [110]
Table 3.1: Different methodologies for human centric IS design, as described in [110]
Table 3.2: Cronbach's alpha scale for reliability values
Table 3.2: Cronbach's alpha scale for reliability values
Table 4.1: Questionnaire questions and answer range questions are in Table 4.1.
Table 4.1: Questionnaire questions and answer range questions are in Table 4.1.
Figure 4.1: A snapshot of the spider diagrams produced by the participants to design their systems
Figure 4.1: A snapshot of the spider diagrams produced by the participants to design their systems
Figure 4.2: Early Stage of the theoretical framework
Figure 4.2: Early Stage of the theoretical framework
The layered framework ensures the separation of functions, reusability and flexibility to create a controllers work together so the adaptation can be performed and then presented on the interface
The layered framework ensures the separation of functions, reusability and flexibility to create a controllers work together so the adaptation can be performed and then presented on the interface
Figure 4.5: Suggested Home Page of MyAds
Figure 4.5: Suggested Home Page of MyAds
Figure 5.1: Proposed theoretical framework
Figure 5.1: Proposed theoretical framework
Figure 5.2 shows the initial system architecture and the specified controllers. The layered framework proposes the layers in order to ensure the separation of functions,
Figure 5.2 shows the initial system architecture and the specified controllers. The layered framework proposes the layers in order to ensure the separation of functions,
Figure 5.3: Process break down diagram for MyAds
Figure 5.3: Process break down diagram for MyAds
Figure 5.4: The Use Case for MyAds another advertisement.
Figure 5.4: The Use Case for MyAds another advertisement.
Algorithm 5.1: Creating a storyline The first iteration of the system development has taken place by implementing a web-based
Algorithm 5.1: Creating a storyline The first iteration of the system development has taken place by implementing a web-based
Figure 5.6: A Personalised Advertisement for a Female who is interested in Fashion
Figure 5.6: A Personalised Advertisement for a Female who is interested in Fashion
Table 5.1 introduces the set of questions used to evaluate and reflect upon the proposed research questions. The questions presented in the questionnaire have an exploratory nature; the connection with the
Table 5.1 introduces the set of questions used to evaluate and reflect upon the proposed research questions. The questions presented in the questionnaire have an exploratory nature; the connection with the
Table 5.1: Results from descriptive statistics and significant tests
Table 5.1: Results from descriptive statistics and significant tests
Figure 6.1: Theoretical Framework for Adaptive Advertising
Figure 6.1: Theoretical Framework for Adaptive Advertising
opinion, which might be forgotten by the user when they fill in the subsequent questionnaire. 6.3. System Design Focus Group Study
opinion, which might be forgotten by the user when they fill in the subsequent questionnaire. 6.3. System Design Focus Group Study
Figure 6.3: Most common websites used by the group
Figure 6.3: Most common websites used by the group
Figure 6.5: Group Opinion on Facebook Ads Facebook has introduced advertisements that are to the taste of the users (see Figure 6.5). feedback to the moderator and from what they filled-in in the surveys. The results advocate that indeed a popular social network platform for the selected user group - from both their direc
Figure 6.5: Group Opinion on Facebook Ads Facebook has introduced advertisements that are to the taste of the users (see Figure 6.5). feedback to the moderator and from what they filled-in in the surveys. The results advocate that indeed a popular social network platform for the selected user group - from both their direc
Figure 6.6: Group ideas of Amazon's best features
Figure 6.6: Group ideas of Amazon's best features
Figure 6.7: Group Ideas of Amazon's worse features recommendations in other languages (Figure 6.7).
Figure 6.7: Group Ideas of Amazon's worse features recommendations in other languages (Figure 6.7).
Table 6.1: Raw Data collected from the users and their interpretations MyAds system, as shown in the second column of the table.
Table 6.1: Raw Data collected from the users and their interpretations MyAds system, as shown in the second column of the table.
Table 6.2: List of System Requirements 6.4. Discussions and Conclusions on the Focus Group Experiment
Table 6.2: List of System Requirements 6.4. Discussions and Conclusions on the Focus Group Experiment
place during level two of the adaptation.
place during level two of the adaptation.
Which of the following is within your interest include for their personalisation. As soon as they submit the registration form, they will be directed
Which of the following is within your interest include for their personalisation. As soon as they submit the registration form, they will be directed
Figure 6.12: Initial Recommendation based on directly stated Interests MyAds The dataset includes 5 different categories, based on the interests, which are: clothing, toys and
Figure 6.12: Initial Recommendation based on directly stated Interests MyAds The dataset includes 5 different categories, based on the interests, which are: clothing, toys and
MyAds Figure 6.13: Options for lack of interest
MyAds Figure 6.13: Options for lack of interest
MyAds
MyAds
If the user actually clicks on a product that he/she want to explore more, the following page will
If the user actually clicks on a product that he/she want to explore more, the following page will
an adaptive story line. The user also has the option to return to the product list, or start a new search, as part of the direct guidance adaptation. Moreover, for evaluation purposes, the user can comment, share or rate the product, to show to what extent the user is interested in the product.
an adaptive story line. The user also has the option to return to the product list, or start a new search, as part of the direct guidance adaptation. Moreover, for evaluation purposes, the user can comment, share or rate the product, to show to what extent the user is interested in the product.
Figure 6.18: Amazon re-directed product
Figure 6.18: Amazon re-directed product
Figure 6.19: The new set of recommendation after the initial behaviour on the system The new set recommends the products based on the calculation of TF-IDF and Jaccard similarity,
Figure 6.19: The new set of recommendation after the initial behaviour on the system The new set recommends the products based on the calculation of TF-IDF and Jaccard similarity,
Figure 6.23: Recommendation list updated to include products related to sub profile
Figure 6.23: Recommendation list updated to include products related to sub profile
Events can be created from the user’s home page. Figure 6.25 contains the event creating form and
Events can be created from the user’s home page. Figure 6.25 contains the event creating form and
usability aspects and Table 7.2 addresses the features related to the usefulness aspects. The results from the table above indicate that for the overall aspects related to usability, the users address this hypothesis, two tables are generated. Table 7.1 addresses the features related to the expressed positive feedback. The mean values are dealt with as discussed earlier in Chapter 3. Any
usability aspects and Table 7.2 addresses the features related to the usefulness aspects. The results from the table above indicate that for the overall aspects related to usability, the users address this hypothesis, two tables are generated. Table 7.1 addresses the features related to the expressed positive feedback. The mean values are dealt with as discussed earlier in Chapter 3. Any
Table 7.2 Results for usefulness questions for H1 Additionally, the results regarding the questions related to usefulness are listed in Table 7.2.
Table 7.2 Results for usefulness questions for H1 Additionally, the results regarding the questions related to usefulness are listed in Table 7.2.
Table 7.3: Combined H1 correlation between usability and usefulness Jsability is slightly higher, with a mean (3.62 + 0.93), implying that the majority of participants
Table 7.3: Combined H1 correlation between usability and usefulness Jsability is slightly higher, with a mean (3.62 + 0.93), implying that the majority of participants
Table 7.4: Results for usefulness questions for H1.1
Table 7.4: Results for usefulness questions for H1.1
Table 7.5: Results for usability questions for H1.1 As discussed before, this experiment is highly focused on the functionality of the system. The
Table 7.5: Results for usability questions for H1.1 As discussed before, this experiment is highly focused on the functionality of the system. The
Table 7.6: Combined H1.1 correlation between usability and usefulness For Hypothesis 1.1, the usefulness of the adaptive features has a slightly higher mean than the
Table 7.6: Combined H1.1 correlation between usability and usefulness For Hypothesis 1.1, the usefulness of the adaptive features has a slightly higher mean than the
Table 7.7 Usefulness answers for Hypothesis 1.2
Table 7.7 Usefulness answers for Hypothesis 1.2
Table 7.8: Usability results for Hypothesis 1.2 The usability overall mean value is (3.50 + 0.95) and a mode of 4. These values are just on the
Table 7.8: Usability results for Hypothesis 1.2 The usability overall mean value is (3.50 + 0.95) and a mode of 4. These values are just on the
Table 7.9: Combined H1.2 correlation between usability and usefulness The results show a moderate correlation, which is a not well connected relationship falling in the
Table 7.9: Combined H1.2 correlation between usability and usefulness The results show a moderate correlation, which is a not well connected relationship falling in the
Table 7.10: Usefulness results for Hypothesis 3
Table 7.10: Usefulness results for Hypothesis 3
Table 7.11: Usability results for Hypothesis 3 A standalone system for personalised e-advertisements is quite an uncommon approach among
Table 7.11: Usability results for Hypothesis 3 A standalone system for personalised e-advertisements is quite an uncommon approach among
Table 7.12: Combined H3 correlation between usability and usefulness This hypothesis is the first hypothesis to produce a strong correlation between the two measures.
Table 7.12: Combined H3 correlation between usability and usefulness This hypothesis is the first hypothesis to produce a strong correlation between the two measures.
Table 7.13: Analysis of users’ qualitative feedback
Table 7.13: Analysis of users’ qualitative feedback
of 2.3 for the availability of the products, as described in Section 7.3.1.
of 2.3 for the availability of the products, as described in Section 7.3.1.
Figure 7.2: Users’ perception of MyAds’ preferred features
Figure 7.2: Users’ perception of MyAds’ preferred features
Table 7.15: Hypothesis 1.1 - follow up experiment statistical significance tests
Table 7.15: Hypothesis 1.1 - follow up experiment statistical significance tests
Table 7.17: Hypothesis 1.2 - follow up experiment statistical significance tests
Table 7.17: Hypothesis 1.2 - follow up experiment statistical significance tests
Table 7.19: Hypothesis 1.2 - follow up extended measures statistical significance tests
Table 7.19: Hypothesis 1.2 - follow up extended measures statistical significance tests
Table 7.20: Percentage of explicit via implicit UM Descriptive analysis was performed to investigate user perception about the implicit versus the form of registering/logging into the system, as shown in Table 7.21.
Table 7.20: Percentage of explicit via implicit UM Descriptive analysis was performed to investigate user perception about the implicit versus the form of registering/logging into the system, as shown in Table 7.21.
Table 7.21: User reflection of explicit via implicit UM The implicit data collection method was more successful in addressing the user expectations with
Table 7.21: User reflection of explicit via implicit UM The implicit data collection method was more successful in addressing the user expectations with
Table 8.1: Research Questions and their relationship to experiments
Table 8.1: Research Questions and their relationship to experiments
The Database schema is as follows: Figure I.1: Database Schema
The Database schema is as follows: Figure I.1: Database Schema
User modelling Algorithms and Snippet Code Annex IT: Snippet code for various algorithms
User modelling Algorithms and Snippet Code Annex IT: Snippet code for various algorithms
Related topics:
Computer ScienceAdaptive Hypermedia
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved