探花直播 of Cambridge - Ludwig-Maximilians 探花直播 Munich

Trainee teachers made sharper assessments about learning difficulties after receiving feedback from AI

tdk25 — Mon, 11 Apr 2022 08:41:49 +0000

探花直播study, with 178 trainee teachers in Germany, was carried out by a research team led by academics at the 探花直播 of Cambridge and Ludwig-Maximilians-Universit盲t M眉nchen (LMU Munich). It provides some of the first evidence that artificial intelligence (AI) could enhance teachers鈥� 鈥榙iagnostic reasoning鈥�: the ability to collect and assess evidence about a pupil, and draw appropriate conclusions so they can be given tailored support.

During the trial, trainees were asked to assess six fictionalised 鈥榮imulated鈥� pupils with potential learning difficulties. They were given examples of their schoolwork, as well as other information such as behaviour records and transcriptions of conversations with parents. They then had to decide whether or not each pupil had learning difficulties such as dyslexia or Attention Deficit Hyperactivity Disorder (ADHD), and explain their reasoning.

Immediately after submitting their answers, half of the trainees received a prototype 鈥榚xpert solution鈥�, written in advance by a qualified professional, to compare with their own. This is typical of the practice material student teachers usually receive outside taught classes. 探花直播others received AI-generated feedback, which highlighted the correct parts of their solution and flagged aspects they might have improved.

After completing the six preparatory exercises, the trainees then took two similar follow-up tests 鈥� this time without any feedback. 探花直播tests were scored by the researchers, who assessed both their 鈥榙iagnostic accuracy鈥� (whether the trainees had correctly identified cases of dyslexia or ADHD), and their diagnostic reasoning: how well they had used the available evidence to make this judgement.

探花直播average score for diagnostic reasoning among trainees who had received AI feedback during the six preliminary exercises was an estimated 10 percentage points higher than those who had worked with the pre-written expert solutions.

探花直播reason for this may be the 鈥榓daptive鈥� nature of the AI. Because it analysed the trainee teachers鈥� own work, rather than asking them to compare it with an expert version, the researchers believe the feedback was clearer. There is no evidence, therefore, that AI of this type would improve on one-to-one feedback from a human tutor or high-quality mentor, but the researchers point out that such close support is not always readily available to trainee teachers for repeat practice, especially those on larger courses.

探花直播study was part of a research project within the Cambridge LMU Strategic Partnership. 探花直播AI was developed with support from a team at the Technical 探花直播 of Darmstadt.

Riikka Hofmann, Associate Professor at the Faculty of Education, 探花直播 of Cambridge, said: 鈥淭eachers play a critical role in recognising the signs of disorders and learning difficulties in pupils and referring them to specialists. Unfortunately, many of them also feel that they have not had sufficient opportunity to practise these skills. 探花直播level of personalised guidance trainee teachers get on German courses is different to the UK, but in both cases it is possible that AI could provide an extra level of individualised feedback to help them develop these essential competencies.鈥�

Dr Michael Sailer, from LMU Munich, said: 鈥淥bviously we are not arguing that AI should replace teacher-educators: new teachers still need expert guidance on how to recognise learning difficulties in the first place. It does seem, however, that AI-generated feedback helped these trainees to focus on what they really needed to learn. Where personal feedback is not readily available, it could be an effective substitute.鈥�

探花直播study used a natural language processing system: an artificial neural network capable of analysing human language and spotting certain phrases, ideas, hypotheses or evaluations in the trainees鈥� text.

It was created using the responses of an earlier cohort of pre-service teachers to a similar exercise. By segmenting and coding these responses, the team 鈥榯rained鈥� the system to recognise the presence or absence of key points in the solutions provided by trainees during the trial. 探花直播system then selected pre-written blocks of text to give the participants appropriate feedback.

In both the preparatory exercises and the follow-up tasks, the trial participants were either asked to work individually, or assigned to randomly-selected pairs. Those who worked alone and received expert solutions during the preparatory exercises scored, on average, 33% for their diagnostic reasoning during the follow-up tasks. By contrast, those who had received AI feedback scored 43%. Similarly, the average score of trainees working in pairs was 35% if they had received the expert solution, but 45% if they had received support from the AI.

Training with the AI appeared to have no major effect on their ability to diagnose the simulated pupils correctly. Instead, it seems to have made a difference by helping teachers to cut through the various information sources that they were being asked to read, and provide specific evidence of potential learning difficulties. This is the main skill most teachers actually need in the classroom: the task of diagnosing pupils falls to special education teachers, school psychologists, and medical professionals. Teachers need to be able to communicate and evidence their observations to specialists where they have concerns, to help students access appropriate support. 聽

How far AI could be used more widely to support teachers鈥� reasoning skills remains an open question, but the research team hope to undertake further studies to explore the mechanisms that made it effective in this case, and assess this wider potential.

Frank Fischer, Professor of Education and Educational Psychology at LMU Munich, said: 鈥淚n large training programmes, which are fairly common in fields such as teacher training or medical education, using AI to support simulation-based learning could have real value. Developing and implementing complex natural language-processing tools for this purpose takes time and effort, but if it helps to improve the reasoning skills of future cohorts of professionals, it may well prove worth the investment.鈥�

探花直播research is published in Learning and Instruction.

A trial in which trainee teachers who were being taught to identify pupils with potential learning difficulties had their work 鈥榤arked鈥� by artificial intelligence has found the approach significantly improved their reasoning.

It is possible that AI could provide an extra level of individualised feedback to help [teachers] develop these essential competencies

Riikka Hofmann

Annie Spratt

Young boy completes homework

探花直播text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright 漏探花直播 of Cambridge and licensors/contributors as identified.聽 All rights reserved. We make our image and video content available in a number of ways 鈥� as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Attribution

Butterflies are genetically wired to choose a mate that looks just like them

ta385 — Fri, 08 Feb 2019 10:35:48 +0000

A team of academics from the 探花直播 of Cambridge, in collaboration with the Smithsonian Tropical Research Institute in Panama, observed the courtship rituals and sequenced the DNA from nearly 300 butterflies to find out how much of the genome was responsible for their mating behaviour.

聽

探花直播research, published in PLOS Biology, is one of the first ever genome studies to look at butterfly behaviour and it unlocks the secrets of evolution to help explain how new species are formed. Scientists sequenced the DNA from two different species of Heliconius butterflies which live either side of the Andes mountains in Colombia. Heliconians have evolved to produce their own cyanide which makes them highly poisonous and they have distinct and brightly coloured wings which act as a warning to would-be predators.

聽

Professor Chris Jiggins, one of the lead authors on the paper and a Fellow of St John鈥檚 College, said: 鈥淭here has previously been lots of research done on finding genes for things like colour patterns on the butterfly wing, but it鈥檚 been more difficult to locate the genes that underlie changes in behaviour. What we found was surprisingly simple 鈥� three regions of the genome explain a lot of their behaviours. There鈥檚 a small region of the genome that has some very big effects.鈥�

聽

探花直播male butterflies were introduced to female butterflies of two species and were scored for their levels of sexual interest directed towards each. 探花直播scientists rated each session based on the number of minutes of courtship by the male 鈥� shown by sustained hovering near or actively chasing the females.

聽

Unlike many butterflies which use scented chemical signals to identify a mate, Heliconians use their long-range vision to locate the females, which is why it鈥檚 important each species has distinct wing markings. When a hybrid between the two species was introduced, the male would most commonly show a preference for a mate with similar markings to itself. 探花直播research showed the same area of the genome that controlled the coloration of the wings was responsible for defining a sexual preference for those same wing patterns.

聽

Dr Richard Merrill, one of the authors of the paper, based at Ludwig-Maximilians-Universit盲t, Munich, said: 鈥淚t explains why hybrid butterflies are so rare 鈥� there is a strong genetic preference for similar partners which mostly stops inter-species breeding. This genetic structure promotes long-term evolution of new species by reducing intermixing with others.鈥�

聽

探花直播paper is one of two published in PLOS Biology聽and funded by the European Research Council which brought together ten years of research by Professor Jiggins and his team.聽探花直播second study investigated how factors including mate preference act to prevent genetic mixing between the same two species of butterfly. They discovered that despite the rarity of hybrid butterflies 鈥� as a result of their reluctance to mate with one another 鈥� a surprisingly large amount of DNA has been shared between the species through hybridisation. There has been ten times more sharing between these butterfly species than occurred between Neanderthals and humans.

聽

Dr Simon Martin, one of the authors of the second paper, from the 探花直播 of Edinburgh, explained: 鈥淥ver a million years a very small number of hybrids in a generation is enough to significantly reshape the genomes of the these butterflies.鈥�

聽

Despite this genetic mixing, the distinct appearance and behaviours of the two species remain intact, and have not become blended. 探花直播researchers found that there are many areas of the genome that define each species, and these are maintained by natural selection, which weeds out the foreign genes. In particular, the part of the genome that defines the sex of the butterflies is protected from the effects of inter-species mating.聽As with the genetics that control mating behaviour, these genes enable each butterfly type to maintain its distinctiveness and help ensure long-term survival of the species. But can the findings translate into other species including humans?

聽

Professor Jiggins said: 鈥淚n terms of behaviour, humans are unique in their capacity for learning and cultural changes but our behaviour is also influenced by our genes. Studies of simpler organisms such as butterflies can shed light on how our own behaviour has evolved. Some of the patterns of gene sharing we see between the butterflies have also been documented in comparisons of the human and Neanderthal genomes, so there is another link to our own evolution.鈥�

聽

鈥淣ext we would like to know how novel behaviour can arise and what kind of genetic changes you need to alter behaviour. We already know that you can make different wing patterns by editing the genes. These studies suggest that potentially new behaviours could come about by putting different genes together in new combinations.鈥�

聽

References

Martin, S et al. Recombination rate variation shapes barriers to introgression across butterfly genomes. PLOS Biology; 7 Feb 2019; DOI:聽10.1371/journal.pbio.2006288

Merrill, R et al. Genetic dissection of assortative mating behavior. PLOS Biology; 7 Feb 2019; DOI: 10.1371/journal.pbio.2005902

Male butterflies have genes which give them a sexual preference for a partner with a similar appearance to themselves, according to new research.

There鈥檚 a small region of the genome that has some very big effects

Chris Jiggins

Heliconius melpomene amaryllis

Yes

Licence type:

Attribution