Periodic Reporting for period 3 - iRead (Infrastructure and integrated tools for personalized learning of reading skill)
Reporting period: 2020-01-01 to 2021-06-30
Literacy is a critical foundational skill that shapes educational attainment, integration in social life and future employment opportunities (UNESCO, 1958). It is the ability to read and write with understanding that involves a lifelong, intellectual process of gaining meaning from a critical interpretation of written text. Globally, UNESCO reports that there are almost 800 million people who are illiterate. In England, for example, 25% of young adults have poor literacy compared with an average of only 9% in the top performing countries in Europe (Kuczera et al 2016). Illiteracy can result from antecedents such as social opportunity including language and literacy practices at home, efficacy of pedagogical support and the child’s reading difficulties (Rose, 2006). Within compulsory education, about 1 in 10 children are struggling readers who are unable to master decoding as it is traditionally taught, as a result gradually being left behind in the classroom despite their potential. There is increasing evidence to suggest that technology can be used to foster literacy and to our current interest, reading.
The iRead project addressed this need by developing new personalized technologies that met the varied needs of three learner groups: children learning to read, children learning English as a foreign language and children with reading difficulties. The project achieved the following aims:
• Developed open access language resources (domain models and dictionaries) for four languages
• Designed apps that considered both reading comprehension and word decoding skills as equally critical parts of the reading process
• Upgraded learning technologies previously shown to foster reading development into personalized technologies
• Orchestrated the teaching process through (i) learning analytics tools that allowed formative assessment and (ii) learning designs supporting the use of the technology by teachers
• Developed an approach to support teachers in adopting the new learning technologies with their primary school children as part of the process of acquiring reading and writing skills
The iRead project addressed this need by developing new personalized technologies that met the varied needs of three learner groups: children learning to read, children learning English as a foreign language and children with reading difficulties. The project achieved the following aims:
• Developed open access language resources (domain models and dictionaries) for four languages
• Designed apps that considered both reading comprehension and word decoding skills as equally critical parts of the reading process
• Upgraded learning technologies previously shown to foster reading development into personalized technologies
• Orchestrated the teaching process through (i) learning analytics tools that allowed formative assessment and (ii) learning designs supporting the use of the technology by teachers
• Developed an approach to support teachers in adopting the new learning technologies with their primary school children as part of the process of acquiring reading and writing skills
Initially, we gathered teachers’ user requirements for the iRead system. Curricula were reviewed, user stories developed, constraints for the iRead system identified. The second task focused on privacy and security, and in particular data ownership, data storage and data security. The third task captured what is expected from the system in terms of functionality.
We then defined seven ‘domain models’ shaping the project’s learning goals, and developed dictionary content resources used by the project applications. These represented the needs of novice readers in four languages (Greek, English, German, Spanish), struggling readers (English, Greek) and children learning English as a foreign language. Domain models capture the language features that have to be mastered when learning to read. Also, we developed annotated dictionaries which are linked to the domain models form the primary source of educational content. These linguistic resources have been uploaded to and made available through the European Language Grid (ELG).
Using the domain models, the following four personalised learning technologies were designed:
A text classification tool: efforts were directed towards personalising text selection for learners based on their reading needs as well as reading goals.
A literacy game ‘Navigo’ and interactive e-books: we developed games designed to teach reading. The games engags learners across a wide breadth of learning objectives; covering both word and sentence level reading content.
A Reader app ‘Amigo’: the Reader was designed to scaffold children’s reading through personalised embedded supports and other instructional features.
The iRead project partners designed, implemented and deployed the cloud software infrastructure which supports the Navigo game and the Amigo Reader in offering a personalized “learning to read” experience. The infrastructure consists of components handling an array of sophisticated tasks e.g. user and domain modelling, user management.
An evaluation phase followed the development of the above technologies. This focused on Navigo’s and Amigo’s adoption in schools. Students attending primary education across the UK, Spain, Greece, Sweden, Romania and Germany used the apps as part of their classroom learning led by their teachers. Additionally, a series of evaluation studies were carried out to evaluate specific design features of each app in how they support the children’s learning.
To support the analysis of the data collected during the evaluation phase of the project and its monitoring an “Analytics’ system” was developed. Moreover, in support of the “unsupervised-use” of Navigo at home a dedicated web server was activated and user admin tools. Finally, the iRead system was deployed for use by all evaluation pilots, and the system ran in a continuous and stable manner with the support of continous maintenance.
The impact and innovation results of the project were:
• Linguistic resources in four languages to aid future SMEs in the development of new children’s literacy and language technology
• Four personalised learning technologies with two of them tested in schools. This includes the Navigo, which the consortium is seeking to license to a third party
• Engaged and sustained use of the Navigo game by 3,700 children and their teachers in six countries
• Capacity building in schools through teacher training designed to support literacy technology with primary school students. This includes the attendance of 323 teachers/TAs in events
• An evidenced-based approach to designing and delivering professional development in schools providing opportunities for future consultancies
The key research results of the project included:
• A theoretical and reflexive understanding of game task design for literacy and language learning at scale
• An empirical understanding of e-Reader highlighting and game formative feedback in supporting the reading process of young learners, including learner group comparisons
• An empirically-grounded account of technology appropriation processes as it relates to schools
• In addition to the above outputs, which have taken place at a consortium level, a number of partners made focused contributions to specific topics of games-based learning e.g. efficacy studies, investigation of learning curves, comparisons between personalised and teacher led use of games
We then defined seven ‘domain models’ shaping the project’s learning goals, and developed dictionary content resources used by the project applications. These represented the needs of novice readers in four languages (Greek, English, German, Spanish), struggling readers (English, Greek) and children learning English as a foreign language. Domain models capture the language features that have to be mastered when learning to read. Also, we developed annotated dictionaries which are linked to the domain models form the primary source of educational content. These linguistic resources have been uploaded to and made available through the European Language Grid (ELG).
Using the domain models, the following four personalised learning technologies were designed:
A text classification tool: efforts were directed towards personalising text selection for learners based on their reading needs as well as reading goals.
A literacy game ‘Navigo’ and interactive e-books: we developed games designed to teach reading. The games engags learners across a wide breadth of learning objectives; covering both word and sentence level reading content.
A Reader app ‘Amigo’: the Reader was designed to scaffold children’s reading through personalised embedded supports and other instructional features.
The iRead project partners designed, implemented and deployed the cloud software infrastructure which supports the Navigo game and the Amigo Reader in offering a personalized “learning to read” experience. The infrastructure consists of components handling an array of sophisticated tasks e.g. user and domain modelling, user management.
An evaluation phase followed the development of the above technologies. This focused on Navigo’s and Amigo’s adoption in schools. Students attending primary education across the UK, Spain, Greece, Sweden, Romania and Germany used the apps as part of their classroom learning led by their teachers. Additionally, a series of evaluation studies were carried out to evaluate specific design features of each app in how they support the children’s learning.
To support the analysis of the data collected during the evaluation phase of the project and its monitoring an “Analytics’ system” was developed. Moreover, in support of the “unsupervised-use” of Navigo at home a dedicated web server was activated and user admin tools. Finally, the iRead system was deployed for use by all evaluation pilots, and the system ran in a continuous and stable manner with the support of continous maintenance.
The impact and innovation results of the project were:
• Linguistic resources in four languages to aid future SMEs in the development of new children’s literacy and language technology
• Four personalised learning technologies with two of them tested in schools. This includes the Navigo, which the consortium is seeking to license to a third party
• Engaged and sustained use of the Navigo game by 3,700 children and their teachers in six countries
• Capacity building in schools through teacher training designed to support literacy technology with primary school students. This includes the attendance of 323 teachers/TAs in events
• An evidenced-based approach to designing and delivering professional development in schools providing opportunities for future consultancies
The key research results of the project included:
• A theoretical and reflexive understanding of game task design for literacy and language learning at scale
• An empirical understanding of e-Reader highlighting and game formative feedback in supporting the reading process of young learners, including learner group comparisons
• An empirically-grounded account of technology appropriation processes as it relates to schools
• In addition to the above outputs, which have taken place at a consortium level, a number of partners made focused contributions to specific topics of games-based learning e.g. efficacy studies, investigation of learning curves, comparisons between personalised and teacher led use of games
State of the art impacts include:
• The integration of four language domain models and related resources, applied to modelling of learning of three diverse learner groups for a number of applications
• Game activities supporting stages of reading fluency for a range of language levels
• Machine learning based methods for syntax analysis for four languages
• Demonstrating the feasibility of supporting personalized interactive eBooks
• Creating a collection of user-actions during gameplay that can be utilized in research in fields of education and linguistics.
Societal implications:
• More effective personalised teaching practices that apply across different educational contexts
• Improving reading motivation and skills of primary school children
• Teacher training to support the delivery of digital approaches to education
• Raising public awareness on the importance of reading and the opportunities of digital learning
• The integration of four language domain models and related resources, applied to modelling of learning of three diverse learner groups for a number of applications
• Game activities supporting stages of reading fluency for a range of language levels
• Machine learning based methods for syntax analysis for four languages
• Demonstrating the feasibility of supporting personalized interactive eBooks
• Creating a collection of user-actions during gameplay that can be utilized in research in fields of education and linguistics.
Societal implications:
• More effective personalised teaching practices that apply across different educational contexts
• Improving reading motivation and skills of primary school children
• Teacher training to support the delivery of digital approaches to education
• Raising public awareness on the importance of reading and the opportunities of digital learning