Authors

  • Guljamol Kulieva

DOI:

https://doi.org/10.71337/inlibrary.uz.science-research.133030

Keywords:

Artificial Intelligence in Education Adaptive Learning English Language Acquisition AI-powered Language Tools Learner Motivation Personalized Instruction NLP in ELT Data-Driven Language Learning Learner Autonomy Feedback Systems.

Abstract

This research explores the effective use of Artificial Intelligence in crafting customized learning strategies aimed at students who regularly face difficulties in mastering the English language. As AI-enhanced educational tools continue to develop, the potential for delivering personalized instruction has greatly improved. The research explores key obstacles encountered by such learners, analyzes current AI-based educational interventions, and introduces a flexible model for implementing AI-driven adaptive methods tailored to individual learning profiles. The results indicate that AI significantly contributes to enhancing English learning outcomes through individualized support, prompt responses, and continuous encouragement.

background image

ISSN:

2181-3906

2025

International scientific journal

«MODERN

SCIENCE

АND RESEARCH»

VOLUME 4 / ISSUE 8 / UIF:8.2 / MODERNSCIENCE.UZ

171

DEVELOPING ADAPTIVE LEARNING STRATEGIES USING ARTIFICIAL

INTELLIGENCE FOR STUDENTS FACING CHALLENGES IN LEARNING ENGLISH

Kulieva Guljamol Tuymurod kizi

MA student at Webster University in Tashkent.

Email:

guljamolquliyevagmail.com

https://doi.org/10.5281/zenodo.16814312

Abstract

. This research explores the effective use of Artificial Intelligence in crafting

customized learning strategies aimed at students who regularly face difficulties in mastering the
English language. As AI-enhanced educational tools continue to develop, the potential for
delivering personalized instruction has greatly improved. The research explores key obstacles
encountered by such learners, analyzes current AI-based educational interventions, and
introduces a flexible model for implementing AI-driven adaptive methods tailored to individual
learning profiles. The results indicate that AI significantly contributes to enhancing English
learning outcomes through individualized support, prompt responses, and continuous
encouragement.

Keywords:

Artificial Intelligence in Education, Adaptive Learning, English Language

Acquisition, AI-powered Language Tools, Learner Motivation, Personalized Instruction, NLP in
ELT, Data-Driven Language Learning, Learner Autonomy, Feedback Systems.

Introduction

. In today’s rapidly evolving digital landscape, Artificial Intelligence (AI) is

reshaping educational practices across the globe. Among its most impactful uses is the creation
of adaptive learning systems, particularly in English language instruction. Although numerous
English learning materials are available, many students still struggle due to limited language
exposure, diverse learning preferences, low confidence, or cognitive obstacles. This thesis
investigates how AI tools can assist these learners by offering customized solutions aligned with
their personal learning profiles and objectives.

Challenges Faced by Students in Learning English

. English language learners often

face multiple barriers, especially when traditional instruction fails to accommodate their specific
learning needs. Some of them:

Lack of Motivation

: One of the fundamental psychological factors influencing the success

of English language learners is motivation. When learners are not sufficiently motivated

either

intrinsically or extrinsically

their willingness to engage with the language meaningfully tends

to decline. According to Dörnyei (2001), lack of motivation can severely hinder classroom

participation, persistence, and progress, especially in environments that fail to stimulate curiosity
or offer personalized support.

Language Anxiety

:

Fear of making mistakes hinders active participation.

Limited Vocabulary and Grammar Retention

:

“Traditional memorization methods may

not suit all learners. Traditional memorization strategies, while still prevalent in many English
classrooms, often fail to promote deep learning or long-term retention, especially when

disconnected from meaningful context and communicative use” (Nation, 2001, p. 96).

Ineffective Feedback

: One of the persistent barriers in language education arises from the

delivery of poorly constructed feedback, which may be too general, delayed, or disconnected


background image

ISSN:

2181-3906

2025

International scientific journal

«MODERN

SCIENCE

АND RESEARCH»

VOLUME 4 / ISSUE 8 / UIF:8.2 / MODERNSCIENCE.UZ

172

from the learner’s specific performance. As noted by Shute (2008), feedback that is vague or
delayed can be ineffective and may even negatively impact learners’ motivation and progress.

Delayed or generic feedback instead of constructive one can fail to address learners’

actual errors.

Time Constraints

: Many students struggle to balance language learning with other

responsibilities.

These challenges necessitate a more individualized and dynamic educational approach.

Role of Artificial Intelligence in Adaptive Learning.

AI offers dynamic solutions by

adapting teaching content and strategies based on learner behavior and performance. Major
contributions of AI to language education include:

Natural Language Processing

(NLP): Tools like Grammarly and ChatGPT offer

grammar correction and conversational practice. NLP-

based tools, as Pérez

-

Marín and Pascual

-

Nieto (2011) note, allow learners to receive immediate and context-aware language corrections,
enhancing their grammatical and semantic competence.

Machine Learning:

AI algorithms identify patterns in learner responses to personalize

lessons.

Speech Recognition and Feedback:

Apps like ELSA Speak improve pronunciation by

providing instant correction.

Chatbots and Virtual Tutors

: These provide 24/7 interaction and guidance.

Learning Analytics

: AI systems track progress and suggest next steps based on

performance metrics.

Data-driven learning:

Recent advancements in AI-powered educational tools have also

enabled learners to engage with

corpora

-based resources, providing authentic language input and

data-driven insights for developing lexical and grammatical competence (Green, 2018). Beyond
conventional AI applications like virtual tutors and NLP-enhanced feedback systems, corpora-
based learning introduces a powerful, data-rich dimension to language acquisition. Artificial
Intelligence can be trained to extract and present contextually relevant corpus data based on
individual learner errors, facilitating autonomous correction and deeper engagement with
authentic English usage. According to Green (2018), exposure to real-world linguistic input

through corpora significantly enhances learners’ ability to grasp collocations, idiomatic

expressions, and grammatical accuracy

especially for those who struggle with abstract

language rules or memorization techniques.

These technologies form the backbone of adaptive learning strategies, where instruction

dynamically changes to meet the learner’s level and preferences.

Proposed Framework for AI-Assisted Adaptive Strategies

.To address the challenges

of struggling English learners, the following AI-supported framework is proposed:

4.1

Needs Assessment.

Graves (2000) defines needs assessment as “a systematic process

for gathering information about learners and using that information to make decisions about

course content, teaching approaches, and assessment” (p. 98).

Initial AI-driven diagnostics to

identify gaps in grammar, vocabulary, and comprehension.

4.2

Personalization Engine

A machine learning model that adjusts:


background image

ISSN:

2181-3906

2025

International scientific journal

«MODERN

SCIENCE

АND RESEARCH»

VOLUME 4 / ISSUE 8 / UIF:8.2 / MODERNSCIENCE.UZ

173

Content difficulty level
Skill-based tasks (e.g., listening, speaking, writing)
Feedback modality (visual, textual, auditory)
4.3

Interactive Feedback Loops

Using NLP and voice recognition, the system offers instantaneous error correction and

motivational messages tailored to learner input

4.4

Learner Dashboard

A user-friendly interface visually tracks progress, highlights weak areas, and awards

achievement markers to encourage consistency.

4.5

Continuous Adaptation

Based on ongoing interaction, the AI updates learning strategies and content to match

changing learner performance.

4.6.

Learner Autonomy.

One of the most valuable contributions of AI in English

education lies in its support for learner autonomy. As learners are given the ability to choose
content, pace their own progress, and receive tailored feedback, they gradually develop
independent learning habits. Wang and Warschauer (2010) highlight how AI technologies
facilitate this shift by decentralizing the role of the teacher and empowering learners to manage
their own linguistic growth.

5

.

Case Studies and Applications

Several platforms have effectively demonstrated the impact of AI-integrated adaptive

learning in language education. For example

Khan Academy

incorporates intelligent guidance and embedded feedback to support

grammar and reading development.

Lingvist

applies predictive algorithms to identify memory decay patterns, while tools like

Duolingo

maintains user engagement through gamified activities and adjusts task

difficulty based on real-time performance.

ChatGPT

simulate interactive dialogues and assist with writing. As Godwin-Jones (2018)

notes, such systems are capable of tailoring learning pathways to the individual, enhancing both
retention and learner motivation.

6. Ethical and Practical Considerations

Despite its advantages, AI integration raises concerns such as:

Learner data privacy
Bias in algorithmic decision-making
Overdependence on automated systems

.

Moreover, successful implementation requires professional development for teachers,

reliable infrastructure, and inclusive design that accommodates diverse learners.

7. Conclusion

Artificial Intelligence presents transformative possibilities for supporting students with

persistent difficulties in English learning. By delivering customized strategies and timely
interventions, AI bridges learning gaps, builds learner confidence, and enhances outcomes.

However, responsible deployment and ongoing evaluation are essential to ensure ethical,

effective, and inclusive adoption of AI in language education.


background image

ISSN:

2181-3906

2025

International scientific journal

«MODERN

SCIENCE

АND RESEARCH»

VOLUME 4 / ISSUE 8 / UIF:8.2 / MODERNSCIENCE.UZ

174

References

1.

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial Intelligence in Education:

Promises and Implications for Teaching and Learning.

https://curriculumredesign.org

2.

Duolingo Blog. (2023). How Duolingo’s AI adapts to your learning style.

https://blog.duolingo.com

3.

Shute, V. J. (2008). Focus on formative feedback. Review of Educational Research,

78(1), 153

189.

https://doi.org/10.3102/0034654307313795

4.

Graves, K. (2000). Designing language courses: A guide for teachers. Heinle & Heinle.

References

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial Intelligence in Education: Promises and Implications for Teaching and Learning. https://curriculumredesign.org

Duolingo Blog. (2023). How Duolingo’s AI adapts to your learning style. https://blog.duolingo.com

Shute, V. J. (2008). Focus on formative feedback. Review of Educational Research, 78(1), 153–189. https://doi.org/10.3102/0034654307313795

Graves, K. (2000). Designing language courses: A guide for teachers. Heinle & Heinle.