Can computers really mark exams? Benefits of ELT automated assessments

app Languages
Hands typing at a laptop with symbols

Automated assessment, including the use of Artificial Intelligence (AI), is one of the latest education tech solutions. It speeds up exam marking times, removes human biases, and is as accurate and at least as reliable as human examiners. As innovations go, this one is a real game-changer for teachers and students. 

However, it has understandably been met with many questions and sometimes skepticism in the ELT community – can computers really mark speaking and writing exams accurately? 

The answer is a resounding yes. Students from all parts of the world already take AI-graded tests.  aԻ Versanttests – for example – provide unbiased, fair and fast automated scoring for speaking and writing exams – irrespective of where the test takers live, or what their accent or gender is. 

This article will explain the main processes involved in AI automated scoring and make the point that AI technologies are built on the foundations of consistent expert human judgments. So, let’s clear up the confusion around automated scoring and AI and look into how it can help teachers and students alike. 

AI versus traditional automated scoring

First of all, let’s distinguish between traditional automated scoring and AI. When we talk about automated scoring, generally, we mean scoring items that are either multiple-choice or cloze items. You may have to reorder sentences, choose from a drop-down list, insert a missing word- that sort of thing. These question types are designed to test particular skills and automated scoring ensures that they can be marked quickly and accurately every time.

While automatically scored items like these can be used to assess receptive skills such as listening and reading comprehension, they cannot mark the productive skills of writing and speaking. Every student's response in writing and speaking items will be different, so how can computers mark them?

This is where AI comes in. 

We hear a lot about how AI is increasingly being used in areas where there is a need to deal with large amounts of unstructured data, effectively and 100% accurately – like in medical diagnostics, for example. In language testing, AI uses specialized computer software to grade written and oral tests. 

How AI is used to score speaking exams

The first step is to build an acoustic model for each language that can recognize speech and convert it into waveforms and text. While this technology used to be very unusual, most of our smartphones can do this now. 

These acoustic models are then trained to score every single prompt or item on a test. We do this by using human expert raters to score the items first, using double marking. They score hundreds of oral responses for each item, and these ‘Standards’ are then used to train the engine. 

Next, we validate the trained engine by feeding in many more human-marked items, and check that the machine scores are very highly correlated to the human scores. If this doesn’t happen for any item, we remove it, as it must match the standard set by human markers. We expect a correlation of between .95-.99. That means that tests will be marked between 95-99% exactly the same as human-marked samples. 

This is incredibly high compared to the reliability of human-marked speaking tests. In essence, we use a group of highly expert human raters to train the AI engine, and then their standard is replicated time after time.  

How AI is used to score writing exams

Our AI writing scoring uses a technology called . LSA is a natural language processing technique that can analyze and score writing, based on the meaning behind words – and not just their superficial characteristics. 

Similarly to our speech recognition acoustic models, we first establish a language-specific text recognition model. We feed a large amount of text into the system, and LSA uses artificial intelligence to learn the patterns of how words relate to each other and are used in, for example, the English language. 

Once the language model has been established, we train the engine to score every written item on a test. As in speaking items, we do this by using human expert raters to score the items first, using double marking. They score many hundreds of written responses for each item, and these ‘Standards’ are then used to train the engine. We then validate the trained engine by feeding in many more human-marked items, and check that the machine scores are very highly correlated to the human scores. 

The benchmark is always the expert human scores. If our AI system doesn’t closely match the scores given by human markers, we remove the item, as it is essential to match the standard set by human markers.

AI’s ability to mark multiple traits 

One of the challenges human markers face in scoring speaking and written items is assessing many traits on a single item. For example, when assessing and scoring speaking, they may need to give separate scores for content, fluency and pronunciation. 

In written responses, markers may need to score a piece of writing for vocabulary, style and grammar. Effectively, they may need to mark every single item at least three times, maybe more. However, once we have trained the AI systems on every trait score in speaking and writing, they can then mark items on any number of traits instantaneously – and without error. 

AI’s lack of bias

A fundamental premise for any test is that no advantage or disadvantage should be given to any candidate. In other words, there should be no positive or negative bias. This can be very difficult to achieve in human-marked speaking and written assessments. In fact, candidates often feel they may have received a different score if someone else had heard them or read their work.

Our AI systems eradicate the issue of bias. This is done by ensuring our speaking and writing AI systems are trained on an extensive range of human accents and writing types. 

We don’t want perfect native-speaking accents or writing styles to train our engines. We use representative non-native samples from across the world. When we initially set up our AI systems for speaking and writing scoring, we trialed our items and trained our engines using millions of student responses. We continue to do this now as new items are developed.

The benefits of AI automated assessment

There is nothing wrong with hand-marking homework tests and exams. In fact, it is essential for teachers to get to know their students and provide personal feedback and advice. However, manually correcting hundreds of tests, daily or weekly, can be repetitive, time-consuming, not always reliable and takes time away from working alongside students in the classroom. The use of AI in formative and summative assessments can increase assessed practice time for students and reduce the marking load for teachers.

Language learning takes time, lots of time to progress to high levels of proficiency. The blended use of AI can:

  • address the increasing importance of formative assessmentto drive personalized learning and diagnostic assessment feedback 

  • allow students to practice and get instant feedback inside and outside of allocated teaching time

  • address the issue of teacher workload

  • create a virtuous combination between humans and machines, taking advantage of what humans do best and what machines do best. 

  • provide fair, fast and unbiased summative assessment scores in high-stakes testing.

We hope this article has answered a few burning questions about how AI is used to assess speaking and writing in our language tests. An interesting quote from Fei-Fei Li, Chief scientist at Google and Stanford Professor describes AI like this:

“I often tell my students not to be misled by the name ‘artificial intelligence’ — there is nothing artificial about it; A.I. is made by humans, intended to behave [like] humans and, ultimately, to impact human lives and human society.”

AI in formative and summative assessments will never replace the role of teachers. AI will support teachers, provide endless opportunities for students to improve, and provide a solution to slow, unreliable and often unfair high-stakes assessments.

Examples of AI assessments in ELT

At app, we have developed a range of assessments using AI technology.

Versant

The Versant tests are a great tool to help establish language proficiency benchmarks in any school, organization or business. They are specifically designed for placement tests to determine the appropriate level for the learner.

PTE Academic

The  is aimed at those who need to prove their level of English for a university place, a job or a visa. It uses AI to score tests and results are available within five days. 

Read more about the use of AI in our learning and testing here.

Explore our courseware and exams

More blogs from app

  • Image of a woman with a headset looking at her laptop

    Picking the right PTE test: PTE Core vs PTE Academic

    By app Languages

    Reading time: 3 minutes

    When preparing to prove your English proficiency—be it for studying abroad, immigration, or professional goals—selecting the right test is extremely important. PTE, renowned worldwide for its English language assessments, offers various tests catering to different needs, including PTE Core and PTE Academic.

    This blog post aims to clarify the differences between these two tests, helping you pick the test that aligns more with your aspirations.

    Understanding PTE Core and PTE Academic

    PTE is a world-leading provider of English language tests, trusted by universities, colleges, governments and professional bodies across the globe. Test scores are accepted in many countries, but which test you choose depends on where you want to go and your reasons why.

    What is PTE Core?

    PTE Core is the test you need to achieve your Canadian dream, approved for economic visa categories.But if you are looking to study in Canada, that is where PTE Academic comes in, approved for both SDS and non-SDS routes.

    PTE Core invites you to experience a test structure designed to assess your general English skills, as opposed to your Academic English, in a short, computer-based format. PTE Core evaluates all language skills—reading, writing, listening and speaking—in one seamless test.

    What is PTE Academic?

    PTE Academic is often the pathway to enrolment for students wanting to study at top universities. Specifically tailored for the academic environment, PTE Academic scores are widely recognized by institutions and are also accepted for visa purposes by the Australian, New Zealand, and UK Visas and Immigration Service. If your destination is higher education or a professional license abroad, PTE Academic is your way in.

    It's also praised for its ability to accurately reflect the speaking abilities of introverts, making it a considerate option for different personality types.

    Test features and acceptance

    When choosing the PTE test you need, consider the following features:

    Test format

    Both PTE Core and PTE Academic offer a computer-based test, which is excellent news for those who prefer not to have the extra stress of speaking to an examiner. Both tests are split up into three parts: Part 1: Speaking & Writing, Part 2: Reading, and Part 3: Listening.

    Speed of results

    With both tests, the results arrive rapidly—typically in just two business days—due to PTE's unique combination of AI scoring and human expertise that also strives to reduce bias.

    Global recognition

    An impressive list of institutions worldwide recognizes PTE Academic. Its scores are specifically sought after in the academic arena and by Australian, New Zealand, and UK visa authorities. Accepted by over 300 universities across the world, PTE Academic is the English test you need if you are looking to study overseas.

    It is also accepted by the Australian and New Zealand governments for migration visas, so it is the test of choice if that is your dream destination.

    PTE Core is recognized by the Canadian government (IRCC) for all economic visas and permanent residency applications.

    Preparation and support

    For those looking to prepare ahead of the test, be it PTE Academic or PTE Core, app offers a range of supporting resources so you can put your best foot forward on test day.

    For PTE Academic, this includes five unique scored practice tests to give you a feel for the full test experience, what to expect, the type of questions that will be asked, and other .

    For PTE Core, there is a taster test you can try out your skills on, , a handbook, and much more.

    Finding your best fit

    The choice between PTE Core and PTE Academic ultimately hinges on your future plans and destination country.

    To make an informed decision, check out PTE's useful links, which clarify and requirements.

    How do I start studying for PTE?

    Embarking on the journey to master PTE begins with understanding your current level and building a solid study plan tailored to your needs. Arm yourself with our, including practice tests and, to familiarize yourself with the question types and formats you'll encounter.

  • Teenager studying with open books on his bed

    What to expect on the day of your PTE test

    By app Languages

    Reading time: 6.5 minutes

    Embarking on the journey of taking the app Test of English (PTE) can be a nerve-wracking experience, especially if it's a pivotal moment in your study abroad journey or a step towards a career and even permanent residency in an English-speaking country. This comprehensive post is designed to guide you through the entire process, from the moment you decide to take the PTE test to the day you actually sit for it, ensuring a worry-free and breezy experience from start to finish.

    With our detailed walkthrough, you can approach the test with confidence, a sense of preparedness and a calm mind. We'll cover everything you need to know, from what to bring, where to leave your belongings and what to expect. So that when the test day arrives, you can focus on passing your English test and not worry about the small things.

  • Children stood around a whiteboard, one is writing on the whiteboard smiling

    Ink's vital role in education: How colors influence student participation

    By app Languages

    Reading time: 7 minutes

    In this age where screens often dominate our field of vision, the humble ink pen might seem like a relic. Yet, intriguing research is bringing to light the unsung importance of ink in educational settings, particularly in enhancing student engagement and learning.

    Today, we look at the importance of handwriting and ink, and how it still plays a pivotal role in the cognitive development of students.

    The importance of ink and color

    , wrought into our documents and notes through ink, plays a significant role in memory retention and comprehension. Psychologists argue that colors like blue and green foster a sense of calmness and improve focus, making them ideal for environments geared toward learning. Conversely, vibrant colors such as red and orange are thought to stimulate energy and excitement, potentially boosting creativity and critical thinking skills. By strategically incorporating these colors into educational materials, teachers can create a more dynamic and effective learning atmosphere, encouraging students to engage more deeply with the content.

    Delving deeper into the benefits of ink for students

    Writing with ink offers multifaceted benefits in an educational context:

    Enhanced memory and learning

    Research has shown that students remember information better when they write it down by hand rather than typing it. This is attributed to the fact that handwriting requires a bit more effort and thought, leading to deeper processing of the information. For instance, college students were found to recall more information from a lecture when they took notes by hand compared to typing them.

    Brain activation

    Writing by hand activates different brain regions compared to typing. When children write, it stimulates areas of the brain responsible for learning and memory. This stimulation is less pronounced when typing. For example, handwriting has been shown to activate the region of the brain that responds more to handwritten letters than typed letters in young children. For example in James, W. L., & Engelhardt, T. M. (2012) ''. This research highlights how the act of handwriting, as opposed to typing, can influence cognitive development and creative thought processes in young learners.

    Development of fine motor skills and cognitive abilities

    Handwriting also plays a crucial role in the development of fine motor skills and cognitive abilities. It requires a level of hand-eye coordination, attention to detail, and thought about what is being written, which are essential skills for academic success and cognitive development.

    Creativity and thoughtful expression

    Handwriting can spark creativity and encourage more thoughtful expression. Slower than typing, it allows more time for creative ideas to develop and for the writer to choose their words carefully.

    Emotional and therapeutic benefits

    Handwriting can have therapeutic benefits, such as better immune function and reduced symptoms of anxiety and depression. Writing about stressful events by hand can arouse higher emotional levels, leading to greater therapeutic benefits compared to typing. For example, ''digs into the emotional and therapeutic benefits of writing by hand about stressful or significant life events.

    Problem-solving and mindfulness

    The process of handwriting can assist in problem-solving and serves as a mindful activity. Writing out problems can help clarify thoughts and lead to solutions. It also encourages a moment of calm and focus in a fast-paced world​​.

    In conclusion, the act of handwriting not only deepens focus and understanding but also contributes significantly to cognitive development, memory retention, creative thinking, emotional well-being and problem-solving skills. These benefits highlight the importance of maintaining handwriting as a skill, even in an increasingly digital world.

    Practical classroom applications of ink

    Teachers utilize various practical applications of ink in the classroom to enhance learning among students. These methods leverage the cognitive and educational benefits of handwriting:

    Handwritten note-taking

    Encouraging students to take notes by hand during lectures can significantly improve their understanding and retention of the material. . This method forces students to process and rephrase the information in their own words, which aids in deeper learning.

    Journal writing and creative tasks

    Assigning journal writing or creative writing tasks can be an effective way to develop student's writing skills and encourage self-expression. The act of writing by hand can stimulate creativity and thoughtfulness, as evidenced by numerous authors and researchers who advocate for the benefits of handwriting for creative processes.

    Practicing cursive writing

    , in particular, can be beneficial for cognitive development. It requires more complex motor skills and can help in the development of fine motor skills. Moreover, cursive writing can be faster than printing, which might engage students more effectively and give them a sense of personal style and ownership over their writing.

    Handwriting for memory and recall exercises

    Using pen and paper for writing exercises focused on memory and recall can be very effective. For example, having students write summaries of lessons or chapters by hand can help them better remember and understand the content. This method can be particularly useful for complex subjects where comprehension is critical​​.

    Therapeutic writing activities

    Incorporating therapeutic writing activities, such as writing letters or reflective essays, can offer emotional and psychological benefits. This practice can be particularly useful in subjects like literature or social studies, where understanding and expressing emotions are part of the learning process.

    Problem-Solving through writing

    Teachers can use handwriting for problem-solving activities, where students are asked to write out their thought processes when solving complex problems. This can, of course, be particularly useful in subjects like mathematics or science, where breaking down problems into smaller, manageable parts is essential.

    Peer review and handwritten feedback

    Providing handwritten feedback on students' work can be more personal and impactful. Teachers can also encourage students to peer-review each other's handwriting, fostering a more engaging and thoughtful critique process.

    Wrapping up: Ink's enduring relevance in education

    In summary, the use of ink and handwriting in the classroom offers a range of benefits for student learning, from improving memory and understanding to fostering creativity and emotional expression. These methods, supported by research and studies, can be effectively integrated into various teaching strategies to enhance educational outcomes.

    Despite the digital age's allure, ink remains a potent tool in the educational arsenal. By nudging students towards the use of ink and harnessing the power of color, educators can cultivate a more engaging, dynamic and effective learning atmosphere.

    Extra insights for maximizing ink's potential

    • Offer students a diverse palette of ink colors to spark their interest and creativity.
    • Promote the use of handwriting in creative and expressive writing exercises.
    • Develop color-coded educational materials to aid visual learning.
    • Encourage personalized stationery: Inspiring students to use personalized ink pens or stationery can increase their engagement and ownership of their written work. It might also stimulate their interest in practicing handwriting more frequently.
    • Implement ink-based art projects: Integrating art projects that require the use of different ink colors can help students explore their creativity while learning about color theory and its impact on emotions and perceptions.
    • Promote the study of calligraphy: Introducing students to the art of calligraphy can foster an appreciation for handwriting's aesthetic aspects and improve their fine motor skills and concentration.
    • Incorporate ink in digital detox sessions: Allocating specific times during which students are encouraged to use only ink and paper for their work can serve as a digital detox, helping them to focus better and reduce screen time.

    Beyond engagement: The art of handwriting

    An often-overlooked benefit of writing in ink is the improvement of handwriting skills. The focused nature of handwriting demands careful attention to letter and number formation, leading to neater, more legible writing. This skill is invaluable for note-taking efficiency and clarity, especially for when they enter the workforce.

    To sum up, the simple act of using ink can have far-reaching effects on student engagement and learning outcomes. We urge educators to rediscover the power of ink in their classrooms and observe the transformative effects it can have on their students.

    From enhancing memory and promoting creativity, to offering therapeutic benefits and aiding cognitive development, the act of presents a multifaceted tool for educators and students alike. Whilst we continue to advance in a digital age, it's crucial to remember the foundational skills and benefits that handwriting offers.