Diario de Aprendizaje: AI AND LANGUAGE TEACHING: CHALLENGES AND POSSIBILITIES

I decided to take this course because AI is here to stay and I think it can help in the process of teaching and learning a lot, so it is important to know how to manage it and learn to use it.

I've created this blog to keep a record of the course and its resources.

Module 1 – AI and language teaching: an introduction

In this module we found some recommendations:

'The Age of A.I.', a YouTube series

A list of AI AVATAR GENERATORS

First of all, we introduced ourselves and we could use an avatar.

This is mine created with WONDERSHARE.

1.1 AI: A newcomer?

https://en.wikipedia.org/wiki/Computing_Machinery_and_Intelligence

There was a discussion about how to measure the presence of AI and we could check the OCDE AI website.

TRENDS AND DATA

These are my thoughts:

I completely agree with a partner that says that Spain is not a relevant country as regards investment or AI lessons in English. There's a lot to do as regards AI in Spain, but I think we'll improve to keep up the pace.

AI is not the future, it's the present and can be really helpful in any domain.

1.2 What is AI?

POSTER: Five Big Ideas in Artificial Intelligence

The Artificial Intelligence (AI) for K-12 initiative (AI4K12)

Ben Williamson & Rebecca Eynon (2020) Historical threads, missing links, and future directions in AI in education. Learning, Media and Technology, 45:3, 223-235

The discussion was about exploring AI's everyday impact and we could test our knowledge about AI.

Test your awareness of artificial intelligence in everyday life

My results were better than I had expected 6 out of 6 (better than 70% of the public and the same as 30%).

This is my reflection on the topic:

'I know that AI is involved in all types of activities nowadays.

On the one hand, I am excited and happy because it can be really helpful, but, on the other hand, I feel afraid because of the uses it can be given.

As a teacher, I see it as a challenge to learn how to use it to motivate and teach my students, but also to prevent cheating.'

We could get more information:

Pew Research Center, February 2023, “Public Awareness of Artificial Intelligence in Everyday Activities”.

Public Awareness of Artificial Intelligence in Everyday Activities

1.3 AI and Machine Learning

Reading:Miao, F., Holmes, W., Huang, R., & Zhang, H. (2021). UNESCO Publishing.

AI and education: A guidance for policymakers

1.4 AI in Education

The “Beijing Consensus on artificial intelligence and education” promoted in 2019 by UNESCO, was signed by 50 government ministers and vice ministers, as well as around 500 international representatives from more than 100 Member States, United Nations agencies, academic institutions, civil society and the private sector.

This is an important document which collects some of the basic issues and concerns regarding AI.

The Consensus describes possibilities and challenges of AI in Education:

Planning AI in education policies,
AI for education management and delivery,
AI to empower teaching and teachers,
AI for learning and learning assessment,
Development of values and skills for life and work in the AI era,
AI for offering lifelong learning opportunities for all,
Promoting equitable and inclusive use of AI in education,
Gender-equitable AI and AI for gender equality,
Ensuring ethical, transparent and auditable use of education data and algorithms, and
Monitoring, evaluation and research.

There was a discussion about which of the promises that appear in the document sound more interesting or provocative.

Of course, a partner wrote about the possibility that AI could replace teachers in the future since this is a topic that always comes to our mind.

I answered the post

'I think AI can help us a lot, but it can't replace us at all. Our job doesn't only consist in providing knowledge, but it also involves feelings, emotions, relating with our students, school partners, ... and AI can't do that (It would be terrible if it could!!!).'

1.5 AI in Education: some examples

Chen, L., Chen, P. and Lin, Z. (2020)

"Artificial Intelligence in Education: A Review"

Zhang, K., & Aslan, A. B. (2021). Computers and Education: Artificial Intelligence.

AI technologies for education: Recent research & future directions

Ouyang, F., & Jiao, P. (2021).

Artificial intelligence in education: The three paradigms. Computers and Education: Artificial Intelligence

Module 2 – Towards AI-powered Language Teaching and Learning: strategies and resources

2.1 AI application to language learning: a review

Jiang (2022) introduces six “dominant forms of AI application in the EFL context”:

Automatic Evaluation Systems
Neural Machine Translation Tools
Intelligent Tutoring Systems
AI Chatbots (and chatting robots)
Intelligent Virtual Environment
Affective Computing (in Intelligent Tutoring Systems).

Similarly, Gkountara and Prasad (2022) describe twelve different ways AI may contribute to language learning:

2.2 Automatic evaluation systems

Examples of automated writing evaluation:

- Criterion

- Pigai

Automated writing evaluation can be incorporated into AI-empowered writing assistants, such as Grammarly

2.3 AI-powered translation (Neural machine translation tools)

According to Klimova et al. (2023), NMT tools are beneficial for FLL.

- NMT can improve students’ L2 translation activities and experience, especially in the area of written comprehension, vocabulary in context, and as a quick language checker for short utterances

- NMT helps beginning students to communicate better or with less effort if it is used by an experienced teacher who can provide them with certain guidelines

- Students with higher proficiency, they may become more aware of the language functions and thus develop their metalinguistic awareness of language differences between L1 and L2

So, in conclusion, NMT tools are especially suitable for advanced learners of L2 who have a higher proficiency level of L2 and are able to critically reflect on the output of NMT texts more than beginners or lower-intermediate learners, for whom NMT can actually have a detrimental effect.

Examples of NMT:

- Google Pixel Buds

- DeepL

2.4 AI Chatbots

Kuki

Replika

2.5 AI and the Metaverse

The union of AI and virtual or augmented reality.

Kye et all (2022)

AI powered virtual reality (VR) with educational purposes:

Google Expeditions

Immerse Language Classes, by Meta Quest

Augmented reality (AR):

Mondly AR by Person

2.6 Intelligent tutoring systems

Defined by Paladines and Ramirez (2020) as “computer programs that provide instruction adapted to the needs of individual students; i.e., they perform functions inherent to the tutorial process (presenting information that must be learned, asking questions or assigning tasks, providing feedback, etc.) to cause a cognitive and motivational change in the student. To accomplish this goal, ITSs leverage artificial intelligence techniques to define content models (the subject to be taught) as well as the tutoring strategies to be employed with each student; i.e., they specify “what” and “how” to teach.”

In the following figure, ITS names and main features are introduced by Paladines and Ramirez (2020):

2.7 Further readings

Barrot, J. S. (2022). Integrating Technology into ESL/EFL Writing through Grammarly. RELC Journal, 53(3), 764–768. https://doi.org/10.1177/0033688220966632.
Belda-Medina, J.; Calvo-Ferrer, J.R. Using Chatbots as AI Conversational Partners in Language Learning. Appl. Sci. 2022, 12, 8427. https://doi.org/10.3390/app12178427
Burstein, J., Chodorow, M., & Leacock, C. (2004). Automated Essay Evaluation: The Criterion Online Writing Service. AI Magazine, 25(3), 27. https://doi.org/10.1609/aimag.v25i3.1774.
Gkountara, D. N., & Prasad, R. (2022, October). A review of Artificial Intelligence in Foreign Language Learning. In 2022 25th International Symposium on Wireless Personal Multimedia Communications (WPMC) (pp. 134-139). IEEE. doi: 10.1109/WPMC55625.2022.10014767.
Guo, L., Wang, D., Gu, F. et al. (2021). Evolution and trends in intelligent tutoring systems research: a multidisciplinary and scientometric view. Asia Pacific Educ. Rev. 22, 441–461. https://doi.org/10.1007/s12564-021-09697-7.
Huang, X., Zou, D., Cheng, G., Chen, X., & Xie, H. (2023). Trends, research issues and applications of artificial intelligence in language education. Educational Technology & Society, 26(1), 112-131. Available at https://www.jstor.org/stable/48707971
Jeon, J., Lee, S. and Choe, H. (2023). Beyond ChatGPT: A conceptual framework and systematic review of speech-recognition chatbots for language learning. Computers and Education, 206, 104898. https://doi.org/10.1016/j.compedu.2023.104898
Jiang, R. (2022) How does artificial intelligence empower EFL teaching and learning nowadays? A review on artificial intelligence in the EFL context. Front. Psychol. 13:1049401. doi: 10.3389/fpsyg.2022.1049401.
Klimova, B., Pikhart, M., Benites, A.D. et al. Neural machine translation in foreign language teaching and learning: a systematic review. Educ Inf Technol 28, 663–682 (2023). https://doi.org/10.1007/s10639-022-11194-2.
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023). ChatGPT for Language Teaching and Learning. RELC Journal, 54(2), 537–550. https://doi.org/10.1177/00336882231162868
Kurni, M., Mohammed, M. S., & Srinivasa, K. G. (2023). Intelligent Tutoring Systems. In A Beginner's Guide to Introduce Artificial Intelligence in Teaching and Learning (pp. 29-44). Cham: Springer International Publishing.
Kye, B., Han, N., Kim, E., Park, Y., & Jo, S. (2021). Educational applications of metaverse: possibilities and limitations. Journal of Educational Evaluation for Health Professions, 18. DOI: https://doi.org/10.3352/jeehp.2021.18.32.
Nazari, N., Shabbir, M. S., & Setiawan, R. (2021). Application of Artificial Intelligence powered digital writing assistant in higher education: randomized controlled trial. Heliyon, 7(5). https://doi.org/10.1016/j.heliyon.2021.e07014.
Ng, D. T. K. (2022). What is the metaverse? Definitions, technologies and the community of inquiry. Australasian Journal of Educational Technology, 38(4), 190-205. https://doi.org/10.14742/ajet.7945.
Paladines, J. and Ramirez, J. (2020). "A Systematic Literature Review of Intelligent Tutoring Systems With Dialogue in Natural Language," in IEEE Access, vol. 8, pp. 164246-164267, doi: 10.1109/ACCESS.2020.3021383.
Polakova, P., & Klimova, B. (2023). Using DeepL translator in learning English as an applied foreign language–An empirical pilot study. Heliyon, 9(8). https://doi.org/10.1016/j.heliyon.2023.e18595.
Wang, S., Yu, H., Hu, X. and Li, J. (2020), Participant or spectator? Comprehending the willingness of faculty to use intelligent tutoring systems in the artificial intelligence era. Br J Educ Technol, 51: 1657-1673. https://doi.org/10.1111/bjet.12998
Weinberger, M. 2022. What Is Metaverse?—A Definition Based on Qualitative Meta-Synthesis. Future Internet,14,310. https://doi.org/10.3390/fi14110310.
Yang, H., Gao, C. & Shen, Hz. (2023) Learner interaction with, and response to, AI-programmed automated writing evaluation feedback in EFL writing: An exploratory study. Educ Inf Technol. https://doi.org/10.1007/s10639-023-11991-3

In order to end up this Module 2 there was a discussion about the impact of AI in education and language teaching.

The focus was placed on ChatGPT.

Some webliography was suggested:

Large Language Models and Where to Use Them: Part 1: https://txt.cohere.com/llm-use-cases/
Large Language Models and Where to Use Them: Part 2:https://txt.cohere.com/llm-use-cases-p2/

We were asked to read the following article:

ChatGPT for Language Teaching and Learning - Lucas Kohnke, Benjamin Luke Moorhouse, Di Zou, 2023

The aim was to choose a suggestion to incorporporate it in our lessons and to add one of ours.

This was my contribution:

"I've heard about ChatGPT, of course, but I've never used it in my lessons, although I know I will since I think it's a good way to enrich lessons, to motivate students and to keep up with times.

I think it can be really useful, however, I'm afraid that students can use it as a shortcut to have their tasks done quickly and well, which wouldn't help them to learn.

After reading the suggestions to use it, I like the fact that it can explain words and texts and can adapt itself to different levels and, of course, the fact that it can help teachers to prepare questions about texts.

My suggestion:

After having a conversation about a topic they like with ChatGPT students can report it to their partners to practise Reported Speech. It is more motivating and interesting for them to do it like this than reporting a traditional conversation."

Module 3 – Possibilities and Challenges of AI for Language Teaching and Learning

3.1 An introduction to possibilities and challenges of AI for Language Teaching and Learning

Technology and AI have brought new concepts to second language teaching and learning in the digital era:

Autonomy: choices and actions of the learner, as well as the development of personal attributes such as initiative, persistence or creativity, to which must be added the recognition of the importance of participation in social groups and respect for the autonomous decisions of others

Agency: it includes both the learner's actions (that is, their interaction with other people and the surrounding environment) and the perception of his or her own agency and of the environment

One of the key issues in the new context of technology-supported language learning is the importance of feedback and error handling. Several authors (Lee, 2016) recognize the importance of affective support and appropriate feedback in relation to the task and the situation for online and hybrid learning, which opens up very interesting possibilities for Artificial Intelligence, which is already able to provide feedback appropriate to the type of task and problem encountered by the learner.

Then there was a discussion about opportunities and challenges of AI. We had to do several tasks:

1. Prepare a list of questions we'd like to ask an expert about the relationship between AI and language learning.

2. Download the following article

3. Use ChatPDF to interact with the article and ask our questions

4. Ask the same questions to Consensus: https://consensus.app/

We were given some other tools:

https://researcherssite.com/the-best-8-ai-powered-tools-for-literature-review/

It was the first time that I used ChatPDF and CONSENSUS and it was amazing!

These are my results:

USING CHATPDF

1. How can AI help in language learning?

AI can help in language learning in a number of ways. For example, AI-powered chatbots can provide learners with opportunities to practice their language skills in a safe and low-pressure environment, and can offer personalized feedback and support. Automated writing evaluation tools can help learners improve their writing skills by providing instant feedback on grammar, vocabulary, and style. Machine translation tools can help learners understand texts in a foreign language, while speech-to-text and text-to-speech apps can help learners improve their pronunciation and listening skills. Additionally, AI can help teachers track learners' progress and provide personalized instruction based on their individual needs and learning styles

2. How can AI help language teachers?

AI can help language teachers in a number of ways. For example, AI-powered tools can help teachers track learners' progress and provide personalized instruction based on their individual needs and learning styles. Automated writing evaluation tools can help teachers save time on grading and provide more detailed feedback to learners. Machine translation tools can help teachers understand texts in a foreign language and communicate with learners who speak different languages. Additionally, AI can help teachers develop more effective teaching materials and methods by analyzing large amounts of data on learner performance and identifying patterns and trends.

3. How can AI help language learners?

AI can help language learners in a number of ways. For example, AI-powered chatbots can provide learners with opportunities to practice their language skills in a safe and low-pressure environment, and can offer personalized feedback and support. Automated writing evaluation tools can help learners improve their writing skills by providing instant feedback on grammar, vocabulary, and style. Machine translation tools can help learners understand texts in a foreign language, while speech-to-text and text-to-speech apps can help learners improve their pronunciation and listening skills. Additionally, AI can help learners track their own progress and identify areas where they need to improve, and can provide them with personalized recommendations for further study.

USING CONSENSUS

1. How can AI help in language learning?

It found 8 highly relevant results and this is the summary:

These studies suggest that AI can help in language learning by improving learning user experience solutions, supporting teacher intervention in pedagogical design, and efficiently teaching languages through AI tutor applications and mobile learning principles.

2. How can AI help language teachers?

It found 11 highly relevant results and this is the summary:

These studies suggest that AI can help language teachers by 1) enhancing their knowledge and autonomy, 2) decreasing their workload through classroom orchestration, and 3) supporting teacher training and continuous professional development.

3. How can AI help language learners?

It found 6 highly relevant results and this is the summary:

These studies suggest that AI can help language learners by improving English proficiency through integration with social media and 21st-century skills, and by enhancing AI literacy and problem-solving abilities in STEAM learners.

3.2 Language teaching with technology and AI

3.3 The future of language teaching and learning… driven by AI

UNESCO's International Commission on the Futures of Education's document.

Promises that AI makes:

Promises linked to learning: accessibility to the different resources, enhanced learning experience.
New ways of operating and organising teaching and learning: technology is expected to enable more learners to be served in an open and networked way through LMOOCs, the open, massive, online language courses.
The increased personalisation of learning: In an article published by Chen et al. (2021: 205) reviewing 20 years of attempts to personalise language learning, personalisation is defined as instruction that optimises the pace, approaches, objectives, content and learning activities according to the interests and needs of each individual learner.

This personalisation could lead to a problem with privacy and security of learner data.

Other aspects to take into account:

Technology aspires to connect us to other people, other realities and virtual realities.
The state of permanent communicative availability.
Questioning the figure of the teacher.
The investment in technology.

As a summary:

This reality of a diversified and growing supply of technology-mediated language learning opportunities poses a challenge for the entire language education ecosystem. On the one hand, understanding that there are many different learning contexts and types of learners allows us to understand that not all solutions are valid or necessary for everyone and everywhere, and that this diversity places new demands on teacher training or instructional design. On the other hand, maintaining a reasonable experimental optimism combined with a sceptical and evidence-based approach can allow us to move forward without falling into the clutches of technological solutionism.

Module 4 – Putting AI into practice: The Final Task

It was time for us to create our own learning scenario using AI.

There were some aspects to take into consideration:

Which AI tool would you like to use?
Will you use a chatbot?
Avatars in a VR setting?
Neural Machine Translation?

Once we had created it using an plan we were given, we had to assess 3 peers' work reflecting on what worked, what could be improved and what was interesting.

There are some tips when coming to peer assessment:

Keep it short, but effective
Focus on the strenghts
Spot areas for improvement
Be specific and provide practical suggestions
Give thanks and end on a positive note

We were given a RUBRIC to create ours and assess the others' in a positive way.

This is my final learning scenario:

MY REAL PARTNER vs MY VIRTUAL PARTNER

This is what my colleagues thought of it:

Overall feedback 1

CRITERION 1: You can find the key competences, the 21st century skills apart from the curricular elements that LOMLOE requires.

CRITERION 2: THE LEARNED CENTERED SGTRATEGY IS DESCRIBED and the way the teacher gives them feedback. The 4 sessions are perfectly understood.

CRITERION 3: Resources are listed and a good battery of assessment/evaluation tools

CRITERION 4: It allows, both, the students and the teacher to participate in the proccess with a variety of instruments.

Overall feedback 2

I wanted to express my admiration for the engaging learning scenario you've developed, "My Real Partner vs My Virtual Partner." Your approach to integrating technology, fostering responsible use, and addressing 21st-century challenges is both forward-thinking and impactful.

The clear alignment with the Spanish curriculum, specifically in producing coherent texts, interacting autonomously, and valuing linguistic and cultural diversity, reflects a well-rounded educational strategy.

Your emphasis on 21st-century challenges, such as critical analysis of digital opportunities and developing lifelong learning skills, is particularly commendable. It not only equips students with essential competences but also encourages responsible and ethical use of technology.

The learning objectives encompassing linguistic competence, plurilingual competence, and digital competence demonstrate a holistic approach. The use of reported speech and subsequent interaction with ChatGPT not only reinforces language skills but also integrates technology seamlessly into the learning process.

The step-by-step learning activities, starting with the students choosing a topic, developing questions, and engaging in a conversation, provide a structured and interactive approach. This not only reinforces linguistic skills but also encourages critical thinking and collaboration.

Your dedication to motivating students through diverse methodologies and familiarizing them with technology aligns perfectly with the evolving educational landscape.

In summary, your learning scenario is a testament to your dedication to creating a dynamic and forward-thinking learning environment. Kudos on your innovative approach!

Páginas

AI AND LANGUAGE TEACHING: CHALLENGES AND POSSIBILITIES