Robert Hendley | University of Birmingham (original) (raw)

Papers by Robert Hendley

Interacting with Computers, Mar 1, 2019

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Interacting with Computers, Mar 1, 2019

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)

Emoji (the digital pictograms) are crucial features for textual sentiment analysis. However, anal... more Emoji (the digital pictograms) are crucial features for textual sentiment analysis. However, analysing the sentiment roles of emoji is very complex. This is due to its dependency on different factors, such as textual context, cultural perspective, interlocutor's personal traits, interlocutors' relationships or a platforms' functional features. This work introduces an approach to analysing the sentiment effects of emoji as textual features. Using an Arabic dataset as a benchmark, our results confirm the borrowed argument that each emoji has three different norms of sentiment role (negative, neutral or positive). Therefore, an emoji can play different sentiment roles depending upon context. It can behave as an emphasizer, an indicator, a mitigator, a reverser or a trigger of either negative or positive sentiment within a text. In addition, an emoji may have neutral effect (i.e., no effect) on the sentiment of the text.

Interacting with Computers

Adaptive e-learning is becoming increasingly popular as a tool to help learners with dyslexia. It... more Adaptive e-learning is becoming increasingly popular as a tool to help learners with dyslexia. It provides more customized learning experiences based on the learners’ characteristics. Each learner with dyslexia has unique characteristics for which material should ideally be suitably tailored. However, adaptation to the characteristics of learners with dyslexia—in particular, their dyslexia type and reading skill level—is limited. By examining the learning effectiveness of adaptation of learning material based on the learner’s type of dyslexia and reading skill, this study fills a knowledge vacuum in this under-researched area. An empirical evaluation through a controlled experiment with 47 Arabic subjects has been undertaken and assessed using the following metrics: learning gain and learner satisfaction. The findings reveal that adapting learning material to the combination of dyslexia type and reading skill level yields significantly better short- and long-term learning gains and ...

Electronic Workshops in Computing

Dyslexia is a universal reading difficulty independent of ethnicity or race. It is sensitive, tho... more Dyslexia is a universal reading difficulty independent of ethnicity or race. It is sensitive, though, to language and is affected by the language's structure and orthography. Also, there are non-reading difficulties that cooccur with dyslexia, such as memory problems and low levels of self-esteem. Due to the lack of research in the Arabic language, this study aims to understand the needs of Arab learners with dyslexia in order to design adaptive interactive educational tools (IET)s based on their needs. To this end, the common reading and non-reading difficulties of learners with dyslexia and the features that the special education teachers (SPET)s prefer to either add or avoid when designing any IET, were explored in schools in Saudi Arabia, from the SPETs' perspective. It was found that vowel letter dyslexia and visual dyslexia are the most common reading difficulties and that dictation difficulty and attention deficit are the most common nonreading difficulties. Hierarchical and Modelling teaching strategies are the teaching approaches that, from the SPETs' perspective, most improved the reading of learners with dyslexia. Finally, pictures and sounds should be used in the design of IETs, while using many colours and loud sounds should be avoided.

2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)

Electronic Workshops in Computing

E-learning has become a popular tool for helping people with dyslexia to improve their reading, a... more E-learning has become a popular tool for helping people with dyslexia to improve their reading, as it provides interactivity anywhere and at any time. However, most traditional e-learning systems are designed for a generic learner, regardless of each individual's differences and needs. In this context, a successful e-learning system needs to consider the learner's individual characteristics-in particular, their dyslexia type and reading skill level. This can lead to a more appropriate learning experience and interaction. There is, however, a need to understand the value of this adaptation, particularly on the learning gain. This study contributes to research by bridging this under-investigated gap by evaluating the learning effectiveness of adapting material based on the learner's dyslexia type and reading skill. A controlled, between-subjects experiment with 47 subjects is described and the results presented and analysed. The findings indicate that adaptation based on the combination of dyslexia type and reading skill level results in significantly better short-term and long-term learning gains and greater learner satisfaction than non-adapted material. There is also evidence that this benefit transfers to learners' reading performance on unseen material.

Electronic Workshops in Computing

Dyslexia is a universal reading difficulty that can be found everywhere regardless of a person's ... more Dyslexia is a universal reading difficulty that can be found everywhere regardless of a person's ethnicity or race. Its manifestation is language-dependent and is affected by the language's structure and orthography. There is a lack of research into Arabic dyslexia and especially into the benefits of adaptive learning in this domain. This study aims to understand the impact on learners' reading performance, satisfaction and behaviour when matching e-training material to a learner's attributes. The focus is on learners with short vowel dyslexia (SVD). The study was undertaken with 22 female primary school children in Saudi Arabia, who were all native Arabic speakers. An e-training system DysTypeTrain2 was designed and developed to support the study. It was found that both the reading performance and satisfaction of learners with dyslexia were improved in both experimental conditions (SVD group and vowel dyslexia (VD) group), regardless of their dyslexia type, indicating that the system was effective and the learning process was enhanced.

SN Computer Science

The global spread of COVID-19 has shifted the learning process towards e-learning. In this contex... more The global spread of COVID-19 has shifted the learning process towards e-learning. In this context, a critical challenge for researchers is to understand and evaluate the effectiveness of e-learning, especially when the learning is adapted to the needs of individual users. In this work we argue that the learner's perception of the level of usability of a system is a valuable metric that gives an insight into the learners' engagement and motivation to learn. Little attention has been paid to this metric. In this paper we explore why this is important and valuable. We present a case study which uses the System Usability Scale (SUS) questionnaire to measure the user's perception of usability as an indirect (proxy) measure of engagement. A between-subject experiment was conducted with 41 learners with dyslexia. The intervention group used the adaptive version of the e-learning system that matched the material to the needs of the learner. The control group used a standard version. At the end, learning gain and SUS scores were assessed. The correlation between learning performance and the perceived level of usability was positive and moderate (0.517, p < 0.05) among participants in the intervention group. However, learning performance and perceived level of usability were unrelated in the control group (− 0.364, p > 0.05). From this, and other work, it appears that using a learner's assessment of the usability of a system is an effective way to measure their attitude to their learning. It reflects their perception of its suitability to their needs and this, in turn, is likely to affect their engagement and motivation. As such, this provides an effective instrument to judge whether adaptation based on learner needs has been successful.

IEEE Transactions on Sustainable Computing, 2022

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

With the explosion of social media usage, researchers have become interested in understanding and... more With the explosion of social media usage, researchers have become interested in understanding and analysing the sentiment of the language used in textual digital communications. One particular feature is the use of emoji. These are pictographs that are used to augment the text. They might represent facial expressions, body language, emotional intentions or other things. Despite the frequency with which they are used, research on the interpretation of emoji in languages other than English, such as Arabic, is still in its infancy. This paper analyses the use of emoji in Arabic social media datasets to build a better understanding of sentiment indicators in textual contents. Seven benchmark Arabic datasets containing emoji were manually and automatically annotated for sentiment value. A quantitative analysis of the results shows that emoji are sometimes used as true/direct sentiment indicators. However, the analysis also reveals that, for some emoji and in some contexts, the role of em...

Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct, 2016

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct, 2016

Hoarding disorder is a complex condition that has attracted little research attention, despite ad... more Hoarding disorder is a complex condition that has attracted little research attention, despite adversely affecting 2-5% of the population. We review the options and difficulties in the treatment of hoarding disorder using technology. We present a novel intervention design, delivered on tablets, that combines a Cognitive Bias Modification game with goal tracking functionality. We outline two experiments in progress: a lab study to measure the impact of our game on a non-hoarding population, and a probe study to determine the suitability of the intervention for participants with hoarding disorder.

The growing reliance on e-learning environments in business and academia is marked by an increasi... more The growing reliance on e-learning environments in business and academia is marked by an increasing interest in the design and development of learning objects and learning management systems (LMS). An LMS provides a framework for courseware creation from learning object, and offers a rich environment where interactions between learner, learning content and instructors can take place. There is a general consensus, however, that their usefulness and relevance depend to a large extent on an awareness of, and compliance with, e-learning architectural and packaging standards. In this paper a number of issues pertinent to effective mediation are addressed. Specific requirements for mediation are identified as part of a wider research programme on learning content mediation. An IMS compliant learning management system and corresponding learning content were developed and presented as an initial stage in the realisation of effective mediation.

Lecture Notes in Computer Science, 2015

Designing effective adap tive e-learning systems, from a usability perspective, represents a chal... more Designing effective adap tive e-learning systems, from a usability perspective, represents a challenge because of the complexity of adaptivity in order to meet the diverse requirements of learners. Furthermore, there is a lack of well-designed experimental evaluation of adaptive e-learning systems in general, and of their usability in particular. The aim of this paper is the presentation of an adaptive e-learning system based on learner knowledge and learning style, and of the results of an initial experimental evaluation of the usability of its two modes of operation. This involves comparing the usability of an adaptive version of the system with the usability of a non-adaptive version, in a learning environment with 75 participants. The experiment produced significant results; they indicate that an adaptive e-learning system based on learner knowledge and learning style has a higher level of perceived usability than a non-adaptive e-learning system. This may also increase the level of satisfaction, engagement and motivation of learners and therefore enhance their learning.

Proceedings of the 13th International Conference on Computer Supported Education

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Blockchain technology holds several promises for many application areas; however, it is not witho... more Blockchain technology holds several promises for many application areas; however, it is not without its limitations. One of the most significant weaknesses of blockchain technology is its substantial energy consumption. Many researchers have proposed solutions to reduce the energy demands of this technology - such as the use of alternative consensus algorithms and the use of renewable energy. However, the use of alternative trust and reputation models to improve sustainability (by, for instance, selecting miners based on these trust or reputation values) has not been widely investigated. In this paper, we propose a reputation model that quantifies and compares the trustworthiness of miners based on their behaviours within a blockchain network. The model is evaluated analytically and compared to other trust and reputation models for miners. The evaluation shows that our model fulfils several desirable properties that should always be satisfied by reputation models, whereas other models do not always meet these requirements. In addition, we perform experimental evaluations to represent the performance of our model and its accuracy in detecting malicious miners. We also report the effectiveness of using the model in reducing the energy consumption of blockchain-based systems.

Interacting with Computers, Mar 1, 2019

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Interacting with Computers, Mar 1, 2019

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Proceedings of the The Seventh Arabic Natural Language Processing Workshop (WANLP)

Emoji (the digital pictograms) are crucial features for textual sentiment analysis. However, anal... more Emoji (the digital pictograms) are crucial features for textual sentiment analysis. However, analysing the sentiment roles of emoji is very complex. This is due to its dependency on different factors, such as textual context, cultural perspective, interlocutor's personal traits, interlocutors' relationships or a platforms' functional features. This work introduces an approach to analysing the sentiment effects of emoji as textual features. Using an Arabic dataset as a benchmark, our results confirm the borrowed argument that each emoji has three different norms of sentiment role (negative, neutral or positive). Therefore, an emoji can play different sentiment roles depending upon context. It can behave as an emphasizer, an indicator, a mitigator, a reverser or a trigger of either negative or positive sentiment within a text. In addition, an emoji may have neutral effect (i.e., no effect) on the sentiment of the text.

Interacting with Computers

Adaptive e-learning is becoming increasingly popular as a tool to help learners with dyslexia. It... more Adaptive e-learning is becoming increasingly popular as a tool to help learners with dyslexia. It provides more customized learning experiences based on the learners’ characteristics. Each learner with dyslexia has unique characteristics for which material should ideally be suitably tailored. However, adaptation to the characteristics of learners with dyslexia—in particular, their dyslexia type and reading skill level—is limited. By examining the learning effectiveness of adaptation of learning material based on the learner’s type of dyslexia and reading skill, this study fills a knowledge vacuum in this under-researched area. An empirical evaluation through a controlled experiment with 47 Arabic subjects has been undertaken and assessed using the following metrics: learning gain and learner satisfaction. The findings reveal that adapting learning material to the combination of dyslexia type and reading skill level yields significantly better short- and long-term learning gains and ...

Electronic Workshops in Computing

Dyslexia is a universal reading difficulty independent of ethnicity or race. It is sensitive, tho... more Dyslexia is a universal reading difficulty independent of ethnicity or race. It is sensitive, though, to language and is affected by the language's structure and orthography. Also, there are non-reading difficulties that cooccur with dyslexia, such as memory problems and low levels of self-esteem. Due to the lack of research in the Arabic language, this study aims to understand the needs of Arab learners with dyslexia in order to design adaptive interactive educational tools (IET)s based on their needs. To this end, the common reading and non-reading difficulties of learners with dyslexia and the features that the special education teachers (SPET)s prefer to either add or avoid when designing any IET, were explored in schools in Saudi Arabia, from the SPETs' perspective. It was found that vowel letter dyslexia and visual dyslexia are the most common reading difficulties and that dictation difficulty and attention deficit are the most common nonreading difficulties. Hierarchical and Modelling teaching strategies are the teaching approaches that, from the SPETs' perspective, most improved the reading of learners with dyslexia. Finally, pictures and sounds should be used in the design of IETs, while using many colours and loud sounds should be avoided.

2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)

Electronic Workshops in Computing

E-learning has become a popular tool for helping people with dyslexia to improve their reading, a... more E-learning has become a popular tool for helping people with dyslexia to improve their reading, as it provides interactivity anywhere and at any time. However, most traditional e-learning systems are designed for a generic learner, regardless of each individual's differences and needs. In this context, a successful e-learning system needs to consider the learner's individual characteristics-in particular, their dyslexia type and reading skill level. This can lead to a more appropriate learning experience and interaction. There is, however, a need to understand the value of this adaptation, particularly on the learning gain. This study contributes to research by bridging this under-investigated gap by evaluating the learning effectiveness of adapting material based on the learner's dyslexia type and reading skill. A controlled, between-subjects experiment with 47 subjects is described and the results presented and analysed. The findings indicate that adaptation based on the combination of dyslexia type and reading skill level results in significantly better short-term and long-term learning gains and greater learner satisfaction than non-adapted material. There is also evidence that this benefit transfers to learners' reading performance on unseen material.

Electronic Workshops in Computing

Dyslexia is a universal reading difficulty that can be found everywhere regardless of a person's ... more Dyslexia is a universal reading difficulty that can be found everywhere regardless of a person's ethnicity or race. Its manifestation is language-dependent and is affected by the language's structure and orthography. There is a lack of research into Arabic dyslexia and especially into the benefits of adaptive learning in this domain. This study aims to understand the impact on learners' reading performance, satisfaction and behaviour when matching e-training material to a learner's attributes. The focus is on learners with short vowel dyslexia (SVD). The study was undertaken with 22 female primary school children in Saudi Arabia, who were all native Arabic speakers. An e-training system DysTypeTrain2 was designed and developed to support the study. It was found that both the reading performance and satisfaction of learners with dyslexia were improved in both experimental conditions (SVD group and vowel dyslexia (VD) group), regardless of their dyslexia type, indicating that the system was effective and the learning process was enhanced.

SN Computer Science

The global spread of COVID-19 has shifted the learning process towards e-learning. In this contex... more The global spread of COVID-19 has shifted the learning process towards e-learning. In this context, a critical challenge for researchers is to understand and evaluate the effectiveness of e-learning, especially when the learning is adapted to the needs of individual users. In this work we argue that the learner's perception of the level of usability of a system is a valuable metric that gives an insight into the learners' engagement and motivation to learn. Little attention has been paid to this metric. In this paper we explore why this is important and valuable. We present a case study which uses the System Usability Scale (SUS) questionnaire to measure the user's perception of usability as an indirect (proxy) measure of engagement. A between-subject experiment was conducted with 41 learners with dyslexia. The intervention group used the adaptive version of the e-learning system that matched the material to the needs of the learner. The control group used a standard version. At the end, learning gain and SUS scores were assessed. The correlation between learning performance and the perceived level of usability was positive and moderate (0.517, p < 0.05) among participants in the intervention group. However, learning performance and perceived level of usability were unrelated in the control group (− 0.364, p > 0.05). From this, and other work, it appears that using a learner's assessment of the usability of a system is an effective way to measure their attitude to their learning. It reflects their perception of its suitability to their needs and this, in turn, is likely to affect their engagement and motivation. As such, this provides an effective instrument to judge whether adaptation based on learner needs has been successful.

IEEE Transactions on Sustainable Computing, 2022

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

With the explosion of social media usage, researchers have become interested in understanding and... more With the explosion of social media usage, researchers have become interested in understanding and analysing the sentiment of the language used in textual digital communications. One particular feature is the use of emoji. These are pictographs that are used to augment the text. They might represent facial expressions, body language, emotional intentions or other things. Despite the frequency with which they are used, research on the interpretation of emoji in languages other than English, such as Arabic, is still in its infancy. This paper analyses the use of emoji in Arabic social media datasets to build a better understanding of sentiment indicators in textual contents. Seven benchmark Arabic datasets containing emoji were manually and automatically annotated for sentiment value. A quantitative analysis of the results shows that emoji are sometimes used as true/direct sentiment indicators. However, the analysis also reveals that, for some emoji and in some contexts, the role of em...

Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct, 2016

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct, 2016

Hoarding disorder is a complex condition that has attracted little research attention, despite ad... more Hoarding disorder is a complex condition that has attracted little research attention, despite adversely affecting 2-5% of the population. We review the options and difficulties in the treatment of hoarding disorder using technology. We present a novel intervention design, delivered on tablets, that combines a Cognitive Bias Modification game with goal tracking functionality. We outline two experiments in progress: a lab study to measure the impact of our game on a non-hoarding population, and a probe study to determine the suitability of the intervention for participants with hoarding disorder.

The growing reliance on e-learning environments in business and academia is marked by an increasi... more The growing reliance on e-learning environments in business and academia is marked by an increasing interest in the design and development of learning objects and learning management systems (LMS). An LMS provides a framework for courseware creation from learning object, and offers a rich environment where interactions between learner, learning content and instructors can take place. There is a general consensus, however, that their usefulness and relevance depend to a large extent on an awareness of, and compliance with, e-learning architectural and packaging standards. In this paper a number of issues pertinent to effective mediation are addressed. Specific requirements for mediation are identified as part of a wider research programme on learning content mediation. An IMS compliant learning management system and corresponding learning content were developed and presented as an initial stage in the realisation of effective mediation.

Lecture Notes in Computer Science, 2015

Designing effective adap tive e-learning systems, from a usability perspective, represents a chal... more Designing effective adap tive e-learning systems, from a usability perspective, represents a challenge because of the complexity of adaptivity in order to meet the diverse requirements of learners. Furthermore, there is a lack of well-designed experimental evaluation of adaptive e-learning systems in general, and of their usability in particular. The aim of this paper is the presentation of an adaptive e-learning system based on learner knowledge and learning style, and of the results of an initial experimental evaluation of the usability of its two modes of operation. This involves comparing the usability of an adaptive version of the system with the usability of a non-adaptive version, in a learning environment with 75 participants. The experiment produced significant results; they indicate that an adaptive e-learning system based on learner knowledge and learning style has a higher level of perceived usability than a non-adaptive e-learning system. This may also increase the level of satisfaction, engagement and motivation of learners and therefore enhance their learning.

Proceedings of the 13th International Conference on Computer Supported Education

Where a licence is displayed above, please note the terms and conditions of the licence govern yo... more Where a licence is displayed above, please note the terms and conditions of the licence govern your use of this document. When citing, please reference the published version. Take down policy While the University of Birmingham exercises care and attention in making items available there are rare occasions when an item has been uploaded in error or has been deemed to be commercially or otherwise sensitive.

Blockchain technology holds several promises for many application areas; however, it is not witho... more Blockchain technology holds several promises for many application areas; however, it is not without its limitations. One of the most significant weaknesses of blockchain technology is its substantial energy consumption. Many researchers have proposed solutions to reduce the energy demands of this technology - such as the use of alternative consensus algorithms and the use of renewable energy. However, the use of alternative trust and reputation models to improve sustainability (by, for instance, selecting miners based on these trust or reputation values) has not been widely investigated. In this paper, we propose a reputation model that quantifies and compares the trustworthiness of miners based on their behaviours within a blockchain network. The model is evaluated analytically and compared to other trust and reputation models for miners. The evaluation shows that our model fulfils several desirable properties that should always be satisfied by reputation models, whereas other models do not always meet these requirements. In addition, we perform experimental evaluations to represent the performance of our model and its accuracy in detecting malicious miners. We also report the effectiveness of using the model in reducing the energy consumption of blockchain-based systems.