Computer-based language assessment: The future is here

David Booth
David Booth
A blonde woman sat at a computer with headphones on in a room with more computers and desks in background

Many people are surprised at the idea of a computer program marking an exam paper. However, computer-based testing already exists in many different formats and many different areas. Many tests or exams that form part of our daily life are taken on computers. If you’ve ever learned to drive, sat a citizenship test, done a training course at work, or completed a placement test for a language course, the odds are that you’ve already taken an automated test.

Yet despite it being so common, there is still a lack of understanding when it comes to computer-based language assessment and how a computer can evaluate productive skills like speaking and writing.

Computer-based testing: a closer look

A common issue is that people have different ideas of what these tests entail. Computers can fulfill several essential roles in the testing process, but these often go unacknowledged. For example, a variety of test questions are needed to administer an exam, along with relevant data, and computers are used to store both the questions and the data. When it comes to creating randomized exams, computer software is used to select the exam questions, based on this data.

Computers can make complex calculations far more quickly and accurately than humans. This means that processes that previously took a long time are completed in days, rather than weeks.

Artificial intelligence (AI) technology is now capable of grading exam papers, for example. This means a shorter wait for exam results. In , candidates receive their results in an average of two days rather than waiting weeks for an examiner to mark their paper by hand.

The benefits for students and teachers

People take exams to prove their skills and abilities. Depending on their goals, the right result can open the door to many new opportunities, whether that is simply moving on to the next stage of a course, or something as life-changing as allowing you to take up your place on a university course in another country.

A qualification can act as a passport to a better career or an enhanced education, and for that reason, it’s important that both students and teachers can have faith in their results.

Computer programs have no inherent bias, which means that candidates can be confident that they will all be treated the same, regardless of their background, appearance or accent. , just one of 蜜桃app’s computer-based exams, offers students the chance to score additional points on the exam with innovative integrated test items.

This integration means that the results are a far more accurate depiction of the candidate’s abilities and provide a truer reflection of their linguistic prowess.

More than questions on a screen

It’s not as easy as simply transferring the questions onto a computer screen. All that does is remove the need for pen and paper; this is a missed opportunity to harness the precision and speed of a computer, as well as its learning potential.

Tests that have been fully digitized, such as PTE Academic, benefit from that automation; eliminating examiner bias, making the test fairer and calculating the results more quickly. Automated testing builds on the technological tradition of opening doors for the future – not closing them.

How technology enhances language testing

The development of automated testing technologies doesn’t merely make the examination process quicker and more accurate – it also gives us the chance to innovate. Speaking assessments are an excellent example of this.

Previously, this part of a language exam involved an interview, led by an examiner, who asked questions and elicited answers. But now that we have the technological capability, using a computer offers students the chance to be tested on a much wider range of speaking skills, without worrying about the inherent bias of the examiner.

Indeed, the use of a computer-based system facilitates integrated skills testing. Traditionally, language exams had separate papers focusing on the four skills of reading, listening, speaking and writing. But the more modern concept of language testing aims to assess these linguistic skills used together, just as they are in real-life situations.

Afterwards, the various scores are categorized to allow learners an insight into their strengths and weaknesses, which helps both students and teachers identify areas which need improvement. This useful feedback is only possible because of the accuracy and detail of automated exam grading.

The space race on paper

Back in the 1960s, during the space race, computers were still a relatively new concept. Kathleen Johnson, one of the first African-American women to work for NASA as a scientist, was a mathematician with a reputation for doing incredibly complex manual calculations. Although computers had made the orbital calculations, the astronauts on the first space flight refused to fly until Kathleen had checked those calculations three times.

This anecdote reminds us that - although computer technology is an inherent part of everyday life - now and then, we still need to check that their systems are working as they should. Human error still comes into play – after all, humans program these systems.

PTE Academic – a fully digitized exam

Every stage of PTE Academic, from registration to practice tests to results (both receiving and sharing them with institutions) happens online. It may come as a surprise to learn that the test itself is not taken online. Instead, students attend one of over 295 test centers to take the exam, which comes with the highest levels of data security.

This means that each student can sit the exam in an environment designed for that purpose. It also allows the receiving institutions, such as universities and colleges, to be assured of the validity of the PTE Academic result.

The future is here

We created computers, but they have surpassed us in many areas – exam grading being a case in point. Computers can score more accurately and consistently than humans, and they don’t get tired late in the day, or become distracted by a candidate’s accent.

The use of AI technology to grade student responses represents a giant leap forward in language testing, leading to fairer and more accurate student results. It also means more consistency in grading which benefits the institutions, such as universities, which rely on these scores to accurately reflect ability.

And here at 蜜桃app, we are invested in staying at the cutting edge of assessment. Our test developers are incorporating AI solutions now, using its learning capacity to create algorithms and build programs that can assess speaking and writing skills accurately and quickly. We’re expanding the horizons of English language assessment for students, teachers and all the other professionals involved in each stage of the language learning journey.

More blogs from 蜜桃app

  • A group of students stood around a teacher on a laptop

    The ethical challenges of AI in education

    提交者 Billie Jago
    Reading time: 5 minutes

    AI is revolutionising every industry, and language learning is no exception. AI tools can provide students with unprecedented access to things like real-time feedback, instant translation and AI-generated texts, to name but a few.

    AI can be highly beneficial to language education by enhancing our students’ process of learning, rather than simply being used by students to ‘demonstrate’ a product of learning. However, this is easier said than done, and given that AI is an innovative tool in the classroom, it is crucial that educators help students to maintain authenticity in their work and prevent AI-assisted ‘cheating’. With this in mind, striking a balance between AI integration and academic integrity is critical.

    How AI impacts language learning

    Generative AI tools such as ChatGPT and Gemini have made it easier than ever for students to refine and develop their writing. However, these tools also raise concerns about whether submitted texts are student-produced, and if so, to what extent. If students rely on text generation tools instead of their own skills, our understanding of our students’ abilities may not reflect their true proficiency.

    Another issue is that if students continue to use AI for a skill they are capable of doing on their own, they’re likely to eventually lose that skill or become significantly worse at it.

    These points create a significant ethical dilemma:

    • How does AI support learning, or does it (have the potential to) replace the learning process?
    • How can educators differentiate between genuine student ability and AI-assisted responses?

    AI-integration strategies

    There are many ways in which educators can integrate AI responsibly, while encouraging our learners to do so too.

    1.?Redesign tasks to make them more ‘AI-resistant’

    No task can be completely ‘AI-resistant’, but there are ways in which teachers can adapt coursebook tasks or take inspiration from activities in order to make them less susceptible to being completed using AI.

    For example:

    • Adapt writing tasks to be hyperlocal or context-specific. Generative AI is less likely to be able to generate texts that are context-bound. Focus on local issues and developments, as well as school or classroom-related topics. A great example is having students write a report on current facilities in their classroom and suggestions for improving the learning environment.
    • Focus on the process of writing rather than the final product. Have students use mind maps to make plans for their writing, have them highlight notes from this that they use in their text and then reflect on the steps they took once they’ve written their piece.
    • Use multimodal learning. Begin a writing task with a class survey, debate or discussion, then have students write up their findings into a report, essay, article or other task type.
    • Design tasks with skill-building at the core. Have students use their critical thinking skills to analyse what AI produces, creatively adapt its output and problem solve by fact-checking AI-generated text.

    2.?Use AI so that students understand you know how to use it

    Depending on the policies in your institution, if you can use AI in the classroom with your students, they will see that you know about different AI tools and their output. A useful idea is to generate a text as a class, and have students critically analyse the AI-generated text. What do they think was done well? What could be improved? What would they have done differently?

    You can also discuss the ethical implications of AI in education (and other industries) with your students, to understand their view on it and better see in what situations they might see AI as a help or a hindrance.

    3.?Use the GSE Learning Objectives to build confidence in language abilities

    Sometimes, students might turn to AI if they don’t know where to start with a task or lack confidence in their language abilities. With this in mind, it’s important to help your students understand where their language abilities are and what they’re working towards, with tangible evidence of learning. This is where the GSE Learning Objectives can help.

    The Global Scale of English (GSE) provides detailed, skill-specific objectives at every proficiency level, from 10 to 90. These can be used to break down complex skills into achievable steps, allowing students to see exactly what they need to do to improve their language abilities at a granular level.

    • Start by sharing the GSE Learning Objectives with students at the start of class to ensure they know what the expectations and language goals are for the lesson. At the end of the lesson, you can then have students reflect on their learning and find evidence of their achievement through their in-class work and what they’ve produced or demonstrated.
    • Set short-term GSE Learning Objectives for the four key skills – speaking, listening, reading and writing. That way, students will know what they’re working towards and have a clear idea of their language progression.
  • A teachet stood in front of a class in front of a board, smiling at his students.

    How to assess your learners using the GSE Assessment Frameworks

    提交者 Billie Jago
    Reading time: 4 minutes

    With language learning, assessing both the quality and the quantity of language use is crucial for accurate proficiency evaluation. While evaluating quantity (for example the number of words written or the duration of spoken production) can provide insights into a learner's fluency and engagement in a task, it doesn’t show a full picture of a learner’s language competence. For this, they would also need to be evaluated on the quality of what they produce (such as the appropriateness, accuracy and complexity of language use). The quality also considers factors such as grammatical accuracy, lexical choice, coherence and the ability to convey meaning effectively.

    In order to measure the quality of different language skills, you can use the Global Scale of English (GSE) assessment frameworks.

    Developed in collaboration with assessment experts, the GSE Assessment Frameworks are intended to be used alongside the GSE Learning Objectives to help you assess the proficiency of your learners.

    There are two GSE Assessment Frameworks: one for adults and one for young learners.

    What are the GSE Assessment Frameworks?

    • The GSE Assessment Frameworks are intended to be used alongside the GSE Learning Objectives to help teachers assess their learners’ proficiency of all four skills (speaking, listening, reading and writing).
    • The GSE Learning Objectives focus on the things a learner can do, while the GSE Assessment Frameworks focus on how well a learner can do these things.
    • It can help provide you with examples of what proficiencies your learners should be demonstrating.??
    • It can help teachers pinpoint students' specific areas of strength and weakness more accurately, facilitating targeted instruction and personalized learning plans.
    • It can also help to motivate your learners, as their progress is evidenced and they can see a clear path for improvement.

    An example of the GSE Assessment Frameworks

    This example is from the Adult Assessment Framework for speaking.

    As you can see, there are sub-skills within speaking (and?for the other three main overarching skills – writing, listening and reading). Within speaking, these are?production?and?fluency, spoken interaction, language range and?accuracy.

    The GSE range (and corresponding CEFR level) is shown at the top of each column, and there are descriptors that students should ideally demonstrate at that level.

    However, it is important to note that students may sit across different ranges, depending on the sub-skill. For example, your student may show evidence of GSE 43-50 production and fluency and spoken interaction, but they may need to improve their language range and accuracy, and therefore sit in a range of GSE 36-42 for these sub-skills.

  • A child sat with a teacher with a tablet

    Writing your own English language materials with the GSE

    提交者 Billie Jago

    Being an English language teacher means you’re also probably (definitely) a materials writer. You likely tailor or create language materials for your students that are suited to their needs and interests, either as supplements to your course materials or for communicative lessons. Alternatively, you might be a teacher who creates paid, published materials available for students worldwide to enjoy.

    With this in mind, think of the materials you’ve developed and ask yourself the following:

    • How do you level your grammar or vocabulary for the content you write?
    • How do you find topic-related vocabulary to extend your students’ knowledge of language?
    • How do you contextualize new grammar or vocabulary?

    You can use many different resources, from online dictionaries to course workbooks to a Google search. Still, the Global Scale of English is a reference that provides everything you need to write great learning materials, all in one place. It can help save you valuable time as a teacher and materials writer.

    For me, the GSE was a game changer as an English teacher, and it continues to be as I write materials. The GSE is not just a tool; it’s a companion in the complex journey of material development, offering clarity and direction at every step. It can guide you in creating effective, engaging learning resources.

    How to use the GSE toolkit to create your own materials

    1. Establishing clear Learning Objectives

    helps you start with a clear roadmap. It provides detailed descriptors for language proficiency at every level, ensuring your materials align with specific learning objectives. For instance, if you’re creating a beginner-level reading comprehension activity, the GSE descriptors will guide you on the appropriate complexity of vocabulary and sentence structures.

    Take a look at the Learning Objectives tab in the GSE Toolkit to learn more.

    2. Designing level-appropriate content

    Once objectives are set, the GSE assists in tailoring the content difficulty to the targeted proficiency level. Its numerical scale, ranging from 10 to 90, allows you to pinpoint the exact level of language skills required and design your materials accordingly. This precision ensures that learners are neither overwhelmed nor under-challenged.

    You can set the level you are looking for by sliding the bar along the scale, so it corresponds to the appropriate CEFR level or GSE range.