English major students’ perceptions towards using the chat gpt ielts writing correction tool for improving ielts writing skills

BANKING ACADEMY FACULTY OF FOREIGN LANGUAGES GRADUATION THESIS ENGLISH-MAJOR STUDENTS’ PERCEPTIONS TOWARDS USING THECHAT GPT IELTS WRITING CORRECTION TOOL FOR IMPROVING IELTS WRITING SKI

BANKING ACADEMY FACULTY OF FOREIGN LANGUAGES

GRADUATION THESIS ENGLISH-MAJOR STUDENTS’ PERCEPTIONS TOWARDS USING THECHAT GPT IELTS WRITING CORRECTION TOOL FOR IMPROVING

IELTS WRITING SKILLS

Student : Dang Thu Thao

CERTIFICATE OF ORIGINALITY

I declare that the graduation thesis entitled “English-Major Students’ Perceptions Towards Using the Chat GPT IELTS Writing Correction Tool for Improving IELTS Writing Skills” is the work conducted by me under the guidance of Dr Hoang Quoc Thinh

The results from the work belong to my research This contributing information derived from other sources is entirely cited and mentioned in the thesis reference

Signature

Name

Date

ACKNOWLEDGEMENTS This section is dedicated to acknowledging the efforts and contributions of the research works of those who came before, as well as the heartfelt support from teachers, family, and friends who have assisted me in completing this research

I would like to extend my sincere gratitude to my teacher and mentor, Dr Hoang Quoc Thinh With his patience, extensive knowledge, and positive encouragement,

he became a significant source of motivation that helped me overcome challenges and complete this thesis Dr Thinh is not only a guide but also an advisor who always listens and provides heartfelt guidance, making this journey much more meaningful

Furthermore, I want to express my deep appreciation to all the English Language Department faculty members at the Banking Academy for the invaluable lessons I have learned throughout my four years of undergraduate study

Moreover, I wish to express my gratitude to my parents I am thankful for their sacrifices and efforts to help me achieve the accomplishments I have today

Lastly, I would like to thank my dear friends, who have accompanied me throughout this journey It is because of them that I feel my four-year university experience has been more meaningful than ever before

TABLE OF CONTENTS

CERTIFICATE OF ORIGINALITY ………2

ACKNOWLEDGEMENTS ………3

TABLE OF CONTENTS……….4

LIST OF ABBREVIATIONS ……….7

LIST OF TABLES ……… 8

LIST OF FIGURES……… 8

ABSTRACT ……… 9

CHAPTER I: INTRODUCTION……… 10

1.1 Background of the study……….10

1.2 Research aim and research questions ……….11

1.3 Significance of the study……….11

1.4 Scope and limitation of the study……….12

1.5 Research structure ……… 12

CHAPTER 2: REVIEW OF RELATED LITERATURE……… 13

2.1 Technology acceptance model………14

2.2 Automated Essay Scoring……… 15

2.3 The IELTS Writing……….15

2.3.1 The IELTS Test……… ………16

2.3.2 IELTS Writing Task……… ……….16

2.3.3 IELTS Writing Band Descriptors……… ……….18

2.3.4 Common Problems of English-Major Students in IELTS Writing Test 18

2.3.4.1 Practice and Feedback……… ……… …….19

2.3.4.2 Vocabulary and Grammar……….……… 19

2.3.4.3 Coherence Errors……… ……….19

2.3.4.4 Task Misinterpretation……… ………….……….19

2.4 Chat GPT IELTS Writing Correction Tool in improving IELTS Writing Skill 2.4.1 Chat GPT……… …….20

2.4.2 Chat GPT IELTS Writing Correction Tool……… …….20

2.5 Review of related studies……….21

2.6.1 Perceived Usefulness……… …… ………23

2.6.2 Perceived Ease of Use……… ….………24

2.6.3 Expectation Confirmation……… ………24

CHAPTER III: RESEARCH METHODOLOGY……… 24

3.1 Research locale………24

3.2 Research design ……… ………26

3.3 Participants……… ………26

3.4 Research instrument………27

3.4 Research instrument………32

3.6 Data analysis……… ………33

CHAPTER 4: FINDINGS AND DISCUSSION……… 38

4.1 The survey data……… ………38

4.1.1 Findings and Discussions of AES ……….……….……… 38

4.1.2 Findings and Discussions of Chat GPT……….………38

4.1.3 Findings and Discussions of Perceived of Ease of Use………….…….41

4.1.4 Findings and Discussions of Perceived of Usefulness………50

4.1.5 Findings and Discussions of Expectation Confirmation…… ………54

4.2 The Semi-Structured Interview Data……… ………54

4.2.1 English-Major Students’ perceptions towards using the Automated Essay Scoring……… ……… ………56

4.2.2 English-Major Students’ perceptions towards the Chat GPT IELTS Writing Correction Tool in general……….………56

4.2.3 English-Major Students’ perceptions towards the Chat GPT IELTS Writing Correction Tool as an easy learning tool……… 56

4.2.4 English-Major Students’ perceptions towards the Chat GPT IELTS Writing Correction Tool as a useful learning tool………… ………57

4.2.5 English-Major Students’ expectations regarding the Chat GPT IELTS Writing Correction Tool……… ………58

4.3 Discussions ……….59

CHAPTER 5: CONCLUSION AND RECOMMENDATIONS 5.1 Summary of findings……… ………60

5.2 Limitations……….……….60

5.3 Recommendation and Implication……… ………61

5.3.1 For English-Major Students ……… ………61

5.3.2 For English teachers……….………61

5.3.3 For future studies……… ………62

REFERENCES………63

APPENDICES ………64

LIST OF ABBREVIATIONS IELTS: International English Language Testing System AES: Automated Essay Scoring

AI: Artifical Intelligence

GPT: Generative Pre-trained Transformer

BELS: Blended E-learning System

LIST OF TABLES AND FIGURES LIST OF TABLES

Table 3.1: Construction of the questionnaire

Table 3.2: Data from the questionnaire coding frame

Table 4.1: Levels of agreement or disagreement

Table 4.2 Reliability Scale of AES

Table 4.3 English-Major Students’ perceptions towards using the Automated EssayScoring

Table 4.4 Reliability Scale of Chat GPT IELTS Writing Correction Tool

Table 4.5 English-Major Students’ perceptions towards the Chat GPT IELTS Writing Correction Tool in general

Table 4.6 Reliability Scale of Perceived of Ease of Use

Table 4.7 English-Major Students’ perceptions towards the Chat GPT IELTSWriting Correction Tool as an easy learning tool

Table 4.8 Reliability Scale of Perceived of Usefulness

Table 4.9 English-Major Students’ perceptions towards the Chat GPT IELTSWriting Correction Tool as a useful learning tool

Table 4.10 Reliability Scale of Expectation Confirmation

Table 4.11 English-Major Students’ expectations regarding the Chat GPT IELTS Writing Correction Tool

LIST OF FIGURES

Figure 1: The Chat GPT IELTS Writing Correction Tool

Figure 2: Three factors in TAM Model

Figure 3: The process used in this study

Figure 4: The four sections of developing the research’s survey

ABSTRACT Recent technological advancements have led to the development of sophisticated artificial intelligence (AI) models, with notable contributions from Chat Generative Pre-trained Transformer (Chat GPT) Particularly, the Covid-19 pandemic has facilitated a shift towards online integrated technology-based learning approaches to adapt to the impacts caused by the pandemic However, this change has brought about

a shift in learners' academic approach as more students have become digital natives seeking learning experiences that transcend barriers of place and time The mixed-methods study aimed at exploring explore English-Major Students’ Perceptionsregarding the use of Chat GPT Writing Correction Tool in Improving IELTS Writing Proficiency, by using the Technology Acceptance Model (TAM) An online survey and a semi-structered interview were used to collect data The survey results demonstrated that English-Major Students held a positive attitude towards the Chat GPT Writing Correction Tool in Learning IELTS Writing Skill According to TAM, learners perceived the Chat GPT Writing Correction Tool as useful and easy to use, considering it as an excellent tool to optimize their time in improving IELTS writing scores by helping them identify and correct grammar, sentence structure, or vocabulary inaccuracies in their writing

Keywords: IELTS Writing Skill, Technology acceptance model, ChatGPT IELTS Writing Correction Tool, Automated Essay Scoring, Perceived Usefulness, Perceived Ease of Use, Expectation Confirmation

CHAPTER I: INTRODUCTION 1.1 Background of the study

Effective knowledge acquisition methods in academia have always been a topic of concern for both students and teachers, as optimizing time and effort to achieve the best results in the teaching and learning process is crucial for improving the quality

of education Especially with the rapid development of artificial intelligence technology, it is not difficult to find integrated learning and teaching methods utilizing AI software as an educational tool Among these methods, the approach to enhancing IELTS writing skills through the support of Automated Essay Scoring (AES) systems has become increasingly popular among the English as a Foreign Language (EFL) student community AES involves being used as a tool to grade academic essays and outline specific essay formats Numerous tools have been developed to help English as a Foreign Language (EFL) students improve their IELTS writing abilities during their preparation process thanks to the rapidly developing field of artificial intelligence technology (Marzuki, Widiati, Rusdin, Darwin, & Indrawati, 2023) Among all the AES systems currently used by learners, the Chat GPT IELTS Writing Correction Tool is evaluated as a useful and user-friendly tool for English as a Foreign Language (EFL) students in enhancing their IELTS writing skills This tool offers numerous benefits to users, not only in improving learners' writing proficiency but also in saving their time and effort Research on AES tools continues to be a hot topic among scientific researchers in this field, and these studies all point to the high applicability of these tools in the IELTS writing learning process In their studies, Kurniati & Fithriani, 2022; Wang, 2022; Zhao, 2023; Syahnaz & Fithriani, 2023, have all acknowledged that the use of AI-powered writing tools can enhance learners' academic writing abilities However, some researchers like Liu et al., 2022; Lund & Wang, 2023, still express concerns about the strong development of AES tools potentially bringing disadvantages to learners in their studies However, this research will investigate the specific tool AES, namely the Chat GPT IELTS Writing Correction Tool, and how English-major

impact of this tool according to students’ perceptions, this research aims to fill thisgap by providing detailed insights into the impact of using the Chat GPT IELTS Writing Correction Tool in IELTS Writing for English-major students’ perceptionsand confirming their expectations after using the Chat GPT IELTS Writing Correction Tool as a learning support tool

1.2 Research aim and research questions

This study aims to explore English- Major Students of Banking Academy’sPerceptions towards improving IELTS Writing skill via the Chat GPT IELTS Writing Correction Tool Finally, to further research, this research can be used as a reflection

on English- Major Students’ attitudes in the direction of learning IELTS Writingthrough AES tool

This research attempt to answer these following questions:

RQ1: What are English-Major students’ perceptions towards the Chat GPT IELTS Writing Correction Tool?

1.3 Significance of the study

This research will be significant for stakeholders involved in enhancing academic writing skills Firstly, specific information about the Chat GPT IELTS Writing Correction Tool will assist English language students currently preparing for or intending to take the IELTS exam, providing them with an additional reference tool

to improve their study efficiency and scores Additionally, educators and instructors

in the field of IELTS training or academic English may consider integrating this tool into their teaching processes to innovate teaching methods and engage learners more effectively Lastly, the findings of this research may prove useful for future studies

on this topic given the rapid advancements in artificial intelligence technology at the present time

1.4 Scope and limitation of the study

Due to time constraints, the research will primarily focus on a group of English language major students at the Banking Academy

1.5 Research structure

The research includes 5 chapters:

Chapter 1 outline the rationale for choosing the subject, as well as the study's aims, scopes and limitations, and structure

Chapter 2 offers a review of related literature on the concept of AES as well as the definition of the Chat GPT IELTS Writing Correction Tool, and how this tool is valued in the area of learning IELTS Writing Skills

Chapter 3 provides an explanation of the research technique In terms of study locations, research design, participants, data collection, research instrument, and statistical treatment

Chapter 4 discusses the findings and results of the research

Chapter 5 is the final chapter of the research, which provides a brief summary and many recommendations for more research

CHAPTER 2: REVIEW OF RELATED LITERATURE

2.1 Technology acceptance model

The TAM model is a theoretical framework developed by Davis in the 1980s based

on the Fishbein and Ajzen (1975) Theory of Reasoned Action (TRA) (Abdullah & Ward, 2016), used to predict and understand user behavior towards technology According to Arning & Ziefle (2007), Technology Acceptance is the process by which an individual or group accepts and uses new technology, including experiencing and evaluating its features, advantages, disadvantages, and how users perceive its use According to Davis, technology acceptance is determined by two main factors: Perceived Ease of Use and Perceived Usefulness Perceived Ease of Use is defined as the extent to which users perceive technology as easy to use and encounter minimal difficulties in accessing and utilizing it, determined by factors such as account login, utilization of technology features, flexibility, and system support The second factor of the model is Perceived Usefulness, which Davis defines

as the extent to which users believe that using technology will benefit them in specific tasks and activities Users will have a high level of technology acceptance when they perceive that the technology tool helps them save time, money, and improve work efficiency

In addition to the two main factors of TAM, there are other variants that extend beyond factors such as beliefs, attitudes, intention to use, actual use, and expectations, helping to further strengthen understanding and provide more accurate predictions of user technology acceptance behavior

Based on the theoretical framework put forth by Davis (1980), many studies have applied TAM to research processes and found that this model can accurately predict and explain the level of user acceptance towards technology such as wireless LAN (Yoon & Kim, 2007); mobile learning (Park, Nam & Cha, 2011; Tai & Ting, 2011); e-learning (Ong & Lai, 2006; Roca & Gagné, 2008); PDAs (Arning & Ziefle, 2007); online communities (Liu, Chen, Sun, Wible & Kuo, 2010)

Related studies mainly focus on aspects of quality, value, and convenience, but there are relatively few studies addressing student satisfaction levels when using such tools,

so this research will further focus on the variable of expectation confirmation

2.2 Automated Essay Scoring

Nowadays, artificial intelligence (AI) technologies have a favorable effect on content writing by offering insightful suggestions and prompts for idea generation and expression Not only limited to providing suggestions for essays and correcting errors, a system has been developed using computer algorithms to evaluate and score essays, known as Automated Essay Scoring (AES) In other words, Automated Essay Scoring is defined as the process of using technology to assess and score essays without human intervention AES typically integrates computer scoring algorithms with software that assists learners in error correction and provides essay prompts to simultaneously analyze and evaluate user-written factors, then automatically assigns scores based on pre-programmed criteria In the field of education, AES systems are considered effective and time-saving essay assessment and scoring systems, especially in exams, assessments, and on websites offering online courses Although the use of AES has its strengths and weaknesses, it remains a valuable tool for improving academic writing skills for English learners Thanks to its outstanding features and high-tech application in the essay grading process, AES has attracted significant attention from practitioners and researchers since its inception over 50 years ago There are numerous software programs or systems developed based on AES for learners of academic writing, such as the Project Essay Grade (PEG); however, the PEG system was frequently criticized for its exclusive attention to surface structures, ignoring content-related aspects and leaving them open to manipulation by manipulators employing commas and extra words (Attali, 2013; Dikli, 2006)

In the 1990s, many AES systems emerged to improve the essay grading process and attempt to avoid similar controversies to PEG Among them, IntelliMetric must be mentioned, an AES system developed by the company Vantage Learning, which uses

factors in an essay and provide immediate scores and feedback on the quality of the writing (Elliott, 2003; Shermis & Barrera, 2002; Shermis, Raymat, & Barrera, 2003) IntelliMetric is a kind of learning engine that internalizes the "pooled wisdom" of knowledgeable human raters via the use of a combination of artificial intelligence (AI), natural language processing (NLP), and statistical technologies (Elliot, 2003, p 71) By utilizing a range of natural language processing methods and a multi-criteria evaluation model for writing quality and performance, IntelliMetric has received positive reviews from the academic writing community and is used in the Writing section of various exams such as the Test of English as a Foreign Language (TOEFL), Scholastic Assessment Test (SAT), and American College Testing (ACT)

2.3 The IELTS Writing

2.3.1 The IELTS Test

Success in international English language tests is becoming more and more important

as a result of an increase in foreign migration to English-speaking nations for employment and education (Green, 2007; Moore & Morton, 2005) Therefore, proficiency assessment exams in English help learners set specific language learning goals and measure their English proficiency not only in everyday situations but also

in advanced academic contexts Trong đó, The popularity of the International EnglishLanguage Testing System (IELTS) is increasing, particularly among Vietnamese students who major in English, as it has seen tremendous development (Nguyen & Tran, 2018) IELTS, which consists of two basic exams (speaking and listening) and two specialized examinations (writing and reading), was initially offered in 1980 and began to be recognized as a prerequisite for courses in English-speaking nations in

1989 Holden and Taylor, 1997) IELTS offers a single exam that may be used to quantify a person's English competence independent of prior knowledge or experience Pearson, William S (2018)

The IELTS exam assesses English proficiency on a scale from 0-9, where each score reflects a different level of English proficiency, ranging from B1 to C1 if using the Common European Framework of Reference for Languages (CEFR) The IELTS exam comprises two main types: IELTS Academic and IELTS General Training The IELTS Academic test focuses on academic content for students intending to study

abroad or participate in academic programs in English-speaking countries The IELTS General Training test delves into everyday real-life situations and work environments, catering to individuals seeking migration or vocational training programs According to statistics, up to 77% of applicants who take the IELTS Academic test also take the proficiency assessment examinations through the IELTS test (IELTS, n.d.) This study primarily focuses on English language major students

at the Banking Academy, hence the research scope is centered on the IELTS Academic test format

2.3.2 IELTS Writing Task

The writing component of the IELTS Academic test is designed based on highly academic criteria for students intending to compile scholarship applications or simply submit applications to universities or other higher education institutions It consists

of two parts: IELTS Writing Task 1 requires candidates to write a summary report based on a provided chart, diagram, or process, while IELTS Writing Task 2 focuses

on essay writing, demanding logical thinking and the ability to use advanced academic language to present opinions and provide arguments and evidence to support their viewpoint The time allocated for candidates to complete Task 1 and Task 2 in the Writing section of the IELTS Academic test is 60 minutes, Veeramuthu a/l Veerappan, Tajularipin Sulaiman (2012) suggests that Task 1 should take around

20 minutes, while Task 2 should take approximately 40 minutes

The topics in Task 2 of the IELTS Writing test often revolve around academic subjects directly related to the fields of study that candidates are pursuing in university or postgraduate programs, or common topics in daily life concerning education, society, and global issues However, for the purpose of performing well

on the IELTS, every student intending to take the test has to have some prior knowledge regarding general social issues (Wilson, 2010)

IELTS examiners who have received training and certification evaluate each writing task separately, assigning Task 2 a higher scoring value than Task 1 (Uysal, 2009) Task 2 typically requires candidates to demonstrate higher-level critical thinking skills and use more advanced language proficiency compared to Task 1, thus

candidates need to effectively organize ideas logically and provide relevant real-life evidence to maintain coherence and defend their viewpoints An important aspect is that Task 2 necessitates a deeper vocabulary and a more diverse grammar structure from candidates compared to Task 1, in order to convey their ideas clearly and succinctly

2.3.3 IELTS Writing Band Descriptors

IELTS establishes criteria descriptions for each score level from band 0 to 9 for the Writing section, and then the writing score, along with scores for other skills, is summed and divided by 4, and rounded to the nearest half or whole number to calculate the final score IELTS examiners evaluate each writing section based on band descriptors, according to Uysal (2009) The method by which these criteria are converted into individual scores is currently unknown Task attainment (TA), coherence and cohesion (CC), lexical resource (LR), and grammatical range and accuracy (GRA) are the four evaluation criteria included in the band descriptors (British Council, n.d.; UCLES, 2004)

Each criterion is evenly spread across the scale from 0 to 9, reflecting varying levels

of proficiency of the candidate corresponding to the respective score This means the description from band 0 to 9 in a continuum increases in importance (Pearson, 2018) Therefore, candidates need to understand the requirements and expectations of the test and examiners, in order to demonstrate their abilities to the best of their potential

in the writing test and to self-improve based on the available criteria All criteria in the Writing test play a crucial role, directly impacting the candidate's final score For Task Achievement, this criterion evaluates the ability to comprehend the issue and meet the requirements of the task, implying that candidates need to ensure addressing all questions adequately through logical argumentation and accurate data Coherence and cohesion evaluate the essay's overall structure (UCLES, 2004) An essay that meets the Coherence and Cohesion (CC) criterion is one that is coherent, easy to understand, and effectively elucidates main and supporting arguments Additionally, the Lexical Resource (LR) criterion assesses the candidate's ability to use a diverse range of vocabulary and avoid basic spelling errors The score for Lexical Resource (LR) depends on the accuracy and richness of the vocabulary used by the candidate

in the test to express their viewpoints and arguments Lastly, the Grammatical Range and Accuracy (GRA) criterion evaluates the candidate's ability to flexibly use various grammatical structures in their writing

It can be observed that, thanks to the clear provision and development of assessment criteria for the Writing test, IELTS learners have been able to clearly identify their learning objectives and recognize their issues during the learning process Henceforth, the issues raised in this study will focus on and refer to one of the four assessment criteria mentioned above

2.3.4 Common Problems of English-Major Students in IELTS Writing Test The Writing test is evaluated as one of the most challenging exams and requires the most English language usage skills compared to other skills in the IELTS test Research has emphasized this (Berman & Cheng, 2001; Kurk & Atay, 2007; Müller, 2015; Sawir, 2005), stating that writing can be a difficult skill for many second language learners As a result, many EFL learners find writing to be confusing and difficult to improve (Berman & Cheng, 2001) And this is supported by statistical data on writing scores, which show that most IELTS test takers receive the lowest writing scores out of all four abilities (IELTS, 2021c) Firstly, several studies addressing the IELTS Writing Test in general will be discussed before delving into research on common issues encountered when improving IELTS writing skills based

on the four scoring criteria mentioned above

2.3.4.1 Practice and Feedback

IELTS students do not have enough time to practice this ability, and they do not receive helpful feedback for their writing, according to a research by Pearson (2018) Perhaps, this is one of the significant reasons leading to poor results in the IELTS Writing section for English language students, as it is a challenging skill that requires

a lot of practice time and specific guidance for learning If learners do not allocate proper time for practicing Writing, it will lead to a decline in writing ability and reduced effectiveness of essay writing Additionally, feedback is an essential factor because if essays are written without accurate feedback for writers to identify their mistakes or gaps in argumentation, learners are likely to follow the same old path and

cannot improve their writing skills As a result, they may not progress but instead struggle with the allocated time in Task 1 and Task 2 (Yao, 2014)

2.3.4.2 Vocabulary and Grammar

One of the most common issues that English language students often encounter when practicing writing skills is limited vocabulary and insufficiently diverse grammar systems to apply in their writing Yao (2014) also pointed out that IELTS test-takers tend to struggle with grammar, vocabulary, lack of fluency in writing, and connectivity due to frequent misuse of complex grammatical structures and linking words in sentences Although these are common difficulties in writing skills that most students face, there are very few research papers addressing these challenges or providing optimal solutions for students to improve these weaknesses

2.3.4.3 Coherence Errors

The study by Panahi and Mohammadi Tabar (2015) indicates that learners often struggle to connect their arguments to provide clear evidence supporting the main points presented in the essay This is particularly true when English-major students face difficulties in using cohesive devices or writing lacking topic sentences in their essays Moreover, many English-major students mistakenly believe that creating more complex sentences will help improve their scores, but this can backfire as too many complex sentences can make the essay convoluted and lacking coherence 2.3.4.4 Task Misinterpretation

One of the most common issues among students when improving their IELTS writing skills is that they often overlook the information provided in the essay prompt and the requirements of the task "Clearly, this will lead candidates to ramble on their own ideas without addressing the main question that needs to be answered or getting off-topic This has been pointed out by Cullen (2017) in his study, suggesting that candidates often misinterpret the task due to subjectively ignoring provided information Additionally, Bagheri and Riasati (2016) also indicated that many learners fail to write focusing on the required aspects and lack balance between arguments in their essays Specifically, candidates may overly focus on one specific idea while neglecting other arguments in the essay, resulting in a low score in the Task Achievement criterion

2.4 Chat GPT IELTS Writing Correction Tool in improving IELTS Writing Skill

2.4.1 Chat GPT

According to Zhou et al (2022), the rapid and extraordinary development of AI technology has expanded opportunities and accessibility for text generation tools such as GPT-3 and ChatGPT OpenAI, a non-profit research company with the aim

of developing and directing AI, released ChatGPT from an improved version of

GPT-3 on November GPT-30, 2022 (Castelvecchi, 2022)

ChatGPT is a language software capable of responding to natural human language and answering automatically, thus it can respond to questions ranging from simple to complex with comprehensive answers Since its release, ChatGPT has received significant public interest, especially from those working in the field of artificial intelligence technology, resulting in numerous studies analyzing the benefits that ChatGPT can bring to specific fields and industries Benedictus et al (2017) stated that the Chatbot Helpdesk assists users in using applications in the Integrated Information System of Sam Ratulangi University Meanwhile, Chen et al (2021) conducted a study supporting the positive impacts that ChatGPT brings to the extrinsic values of customer experience, similar to the conclusions in the research by Astuti & Fatchan (2019) and Hakim et al (2020), which stated that using chatbots can assist with questions, provide services, and enhance customer experience Moreover, Melindah (2020) emphasized that ChatGPT facilitates communication between humans and computers in information searching, allowing buyers to have a clearer view of phone parts to make the best purchasing decisions

2.4.2 Chat GPT IELTS Writing Correction Tool

Chat GPT is an artificial intelligence introduced by OpenAI in 2018, and it has been developed through several stages with continuous improvements from GPT-2 to GPT-4, as of the current time This AI tool is capable of providing logical responses and interacting with users tailored to various conversational scenarios Thanks to its specialized features, Chat GPT has affirmed its optimal role as a versatile and flexible tool for natural language processing and generating texts for users

Due to these features, Chat GPT is a useful tool for English language students to enhance their language proficiency and learning experience, thereby achieving the best results Moreover, there are now more specialized versions of AI-based tools built on the Chat GPT platform and algorithms to create an AES system with the purpose of helping English language students improve their IELTS writing skills and achieve their desired band scores in the IELTS exam, known as the Chat GPT IELTS Writing Correction Tool As of now, there are very few in-depth research studies analyzing the features and mechanisms of the Chat GPT IELTS Writing Correction Tool However, Essel (2023) suggested that with the rapid development of AI technology and learners' demand for easier and more effective approaches to writing skills, Chat GPT may likely be used for AES applications

This research will provide a comprehensive and detailed insight into the Chat GPT IELTS Writing Correction Tool regarding its mechanisms, functions, and convenience when used in the learners' writing process

The Chat GPT IELTS Writing Correction Tool is considered an Automated Essay Scoring system, similar to tools developed based on NLP such as e-rater® or IntelliMetric™ The Chat GPT IELTS Writing Correction Tool utilizes acombination of the available Chat GPT platform along with natural language processing (NPL), statistical algorithms, and the scoring criteria for writing skills in the IELTS Writing test To efficiently integrate the tool into the learning process, learners can use two features of the tool: grading essays and creating outlines To grade essays, learners only need to select the "Grade IELTS Writing Task 1 or Task 2" option, then enter the essay prompt (for Task 1, they need to upload a photo of the prompt or select from the available prompts) in the "Prompt" box and enter the essay content in the "Essay" box, then choose to grade The system will help learners identify errors accurately, analyze specific mistakes in an understandable manner, and grade and provide comments more accurately according to the latest IELTS Writing Band Descriptors For the outline feature for Task 1 and Task 2, it helps learners avoid getting off-topic or being too scattered in irrelevant issues to complete their essays more efficiently

Figure 1: The Chat GPT IELTS Writing Correction Tool

The Chat GPT IELTS Writing Correction Tool has graded and outlined essays for over 1000 users Users can start for free by registering an account on the website and receive 5 free essay grading sessions

2.5 Review of related studies

Many previous studies have delved into the acceptance of AI technology by language learners regarding English writing proficiency It is noteworthy that accumulated evidence from previous studies has examined and confirmed the relatively high acceptance level of English language learners towards integrating technology into the writing process based on Davis's theory (1980)

In 2023, Atsushi Mizumoto conducted a study on the perception of EFL students regarding AI Writing Tools Over 12,100 English essays written by TOEFL test takers in the years 2006 and 2007 were used and analyzed by Atsushi for research purposes During the study, Atsushi utilized the GPT-3 text-davinci-003 model to analyze the essays and draw conclusions about the extent to which AES by GPT predicts the benchmark levels of TOEFL 11 with and without the assistance of research-based linguistic features at the levels of lexis, syntax, and cohesion Furthermore, the study also demonstrated the potential use of GPT in automated essay

GPT, can be useful AES tools for the writing process and emphasized possibilities and considerations while utilizing Chat GPT as an AES tool in academic settings

Similarly, in 2024, 150 active university students participated in a survey on the role

of Chat GPT in the writing process conducted by Zamzam Bibi The study employed

a mixed-method approach, including surveys, interviews, and usability testing, to identify the factors shaping students' perceptions of the Chat GPT tool The results of the study concluded a positive acceptance level of students towards Chat GPT, as well as their satisfaction with the support provided by this tool in the writing process

Likewise, in 2012, Chi-Cheng Chang conducted a study on the perceived convenience factor of university students regarding mobile technology in English learning, based on Davis's TAM Model (1980) In addition to the two main factors of TAM, Chi-Cheng Chang analyzed the perceived convenience factor to explain the influences on the acceptance of learning English through mobile technology 158 university students using personal phones to support their English learning participated in the questionnaire in the study The collected data showed that ease of use, usefulness, and convenience are prerequisite factors influencing the positive acceptance level of students towards technology tools in the English learning process

Ahmed Al-Azwei (2017) conducted an assessment study on the perception of learners towards a blended e-learning system (BELS) based on Davis's TAM Model (1980)

A total of 210 university students participated in the study through a survey tool and the Index of Learning Styles (ILS) Questionnaire The highlight of this study is the integration of perceived satisfaction and technology acceptance in accordance with the psychological traits of learners The research model successfully integrated users' technology usage intentions and satisfaction, however, psychological differences did not directly affect the level of acceptance and future technology usage of students

Based on the aforementioned related studies, it can be observed that learners' acceptance of new AI tools such as Chat GPT is relatively high, and furthermore, the

significant potential that these technology tools bring to users in the academic writing process Additionally, factors in Davis's TAM model (1980) such as ease of use, usefulness, and satisfaction are directly influential on the acceptance and intention to continue using technology in the future of learners However, thanks to Ahmed Al-Azwei's study (2017), psychological factors are further explored in analyzing the acceptance level of learners Ultimately, these studies have laid a basic foundation for further research on the topic of technology in education, and moreover, have proposed many more interesting approaches and new research methods to delve deeper into the integration of technology in academic English writing of English language learners

2.6 Theoretical framework

The theoretical framework of this study is based on the technology acceptance model (TAM) developed by Davis (1989) The technology acceptance model (TAM) is an important model in the study of technology acceptance, based on the Fishbein and Ajzen (1975) Theory of Reasoned Action (TRA) (Abdullah & Ward, 2016) TAM explains user behavior with technology based on two main factors: perceived usefulness and perceived ease of use Many studies have used TAM as a theoretical framework with these two factors to explain the factors driving user adoption and use

of new technology, especially as AI technology is booming in the present era In addition to the two main factors of perceived usefulness and perceived ease of use, according to TAM, several researchers have recognized other external factors that might play crucial roles in strengthening the TAM model For example, Moon and Kim (2001) suggested that learners' adoption of technology might be significantly predicted by perceived fun in addition to utility and simplicity of use Additionally, Ngai, Poon, and Chan (2007) discovered through an empirical study that learners' satisfaction with technical support has a considerable impact on both the usefulness and ease of use components of TAM I do acknowledge the significance of user perception of a completely new technology, but there are still very few comprehensive research on how user happiness with technology influences their adoption of it Therefore, in addition to the two primary external factors—perceived

utility and perceived ease of use—the study will also examine an internal aspect, namely expectation confirmation

2.6.1 Perceived Usefulness

This is an external factor influencing users' acceptance of technology Perceived usefulness indicates users' perception of the extent to which a tool helps them accomplish specific tasks or objectives in their field For example, when users perceive that using technology in work or study helps them save time and effort, and complete tasks effectively in projects, they are more likely to accept and use that technology

2.6.2 Perceived Ease of Use

Perceived ease of use is also an external factor referring to users' perception of the ease of use of the technology It can be observed that users will accept technology when the tool is perceived as easy to use and does not require too much effort or specialized knowledge to operate

2.6.3 Expectation Confirmation

Expectation confirmation is considered an internal or psychological factor, and it is also an extended factor in TAM This factor reflects how the confirmation of expectations can influence the way users evaluate the usefulness of the technology and ultimately affect their acceptance It is closely related to the user's technology acceptance process

This present study is followed by this framework:

Figure 2: Three factors in TAM Model

In summary, this chapter covers basic information about the IELTS Writing skill and the Chat GPT IELTS Writing Correction Tool Regarding the IELTS Writing skill, I have discussed its definition, the exam structure, and the scoring criteria for this skill

in the IELTS test As for the Chat GPT IELTS Writing Correction Tool, I have provided definitions of Automated Essay Scoring systems and how to use the Chat GPT IELTS Writing Correction Tool for essay evaluation Additionally, I have reviewed relevant research studies on this topic, along with theoretical frameworks

to help readers understand the nature of the factors used in the study before proceeding to the next chapter: Research methodology

Perceived

Usefulness

Perceived Ease of Use Expectation Confirmation

CHAPTER III: RESEARCH METHODOLOGY

3.1 Research locale

This research was conducted among English language major students at the Faculty

of Foreign Languages of Banking Academy

3.2 Research design

This study employs a combination of qualitative and quantitative methods through a mixed-methods sequential explanatory research design For the quantitative method, the study utilizes the Likert scale (1932) using the Google Forms website to collect data To gather qualitative information, the study employs semi-structured interviews Finally, from the data collected from these two methods, the research relies on a mixed-methods sequential explanatory research design to provide a comprehensive view of the research issue and thereby offer detailed, rich conclusions and proposed solutions As Pardede (2019) pointed out the significance of using mixed-methods sequential explanatory in research studies, this method provides more accurate and detailed results, supporting researchers in better understanding the issues they are investigating

3.3 Participants

This study was supported by a group of 46 participants who completed an online survey Since the tool under investigation is relatively new and highly updated, and the trend of preparing for the IELTS exam is becoming increasingly popular across all age groups, I aimed to broaden the survey target audience to include all students

at the English Language Department who have been or are currently preparing to take the IELTS exam To ensure the reliability and accuracy of the data, all participants had to be students who had previously used the Chat GPT IELTS Writing Correction Tool in their IELTS writing preparation As a result, there were 46 English language students at the Banking Academy who had used the Chat GPT IELTS Writing Correction Tool, while the remainder were students who did not meet the quality standards (figure 3.1) All participants volunteered to participate in the questionnaire and were assured that their personal information would only be used for research purposes The decision to select English language students who had used the Chat

GPT IELTS Writing Correction Tool as the survey participants for the study was based on several reasons Firstly, English language students at the Banking Academy are potential users of the Chat GPT IELTS Writing Correction Tool as they are likely

to take the IELTS exam for future career-related goals in their field of study Additionally, all students participating in this survey need to have a solid foundation

of knowledge and skills in English language, as this is an important factor in ensuring the collection of high-quality data Moreover, only those who have used the Chat GPT IELTS Writing Correction Tool can provide accurate information about their experience with this tool, enabling an assessment of learners' acceptance of this new type of tool The study will contribute to understanding the perception of using the Chat GPT IELTS Writing Correction Tool in enhancing IELTS Writing proficiency 3.4 Research instrument

The mixed methods approach is an approach that combines quantitative and qualitative methods to collect and analyze data, thereby providing the most comprehensive and clear understanding of English language students' perceptions of the Chat GPT IELTS Writing Correction Tool in their IELTS writing studies In my research, I decided to use this data analysis tool because using both methods in the same study can exploit the advantages of both methods, enhancing the reliability and accuracy of the research results Additionally, I referred to this method from Zamzam Bibi's (2024) research on a topic related to my study Therefore, I believe this is the most reasonable and comprehensive research method for my thesis

The data for this study consisted of the perceptions of English Major Students regarding the use of the Chat GPT IELTS Writing Correction Tool in their writing process, and they were collected through an online survey and interview questions

As cited in Wikipedia, questionnaires are common tools used in scientific research through a series of questions designed to gather data on opinions, perceptions, behaviors, or other related factors This research tool is often efficient and convenient for collecting a large amount of necessary data for the study To conduct this research,

I referred to surveys from related studies such as the work of Shima Balouchi (2020)

on elements influencing learners' intention to utilize technology for informal English

behavioral intention, and reported satisfaction of students through the use of augmented reality For the online survey, this study utilized the five-point Likert scale (1932) through the Google Forms website The five points of the Likert scale applied

in the survey are:

5 may not fully capture the depth of users' opinions Therefore, this study also conducted semi-structured interviews with 5 English-Major Students who had used the Chat GPT IELTS Writing Correction Tool in their IELTS Writing skill preparation before taking the IELTS exam to overcome limitations in the research For the interview questions, there were 5 open-ended questions The study did not set any standards for these questions, so the answers were entirely based on the participants' personal experiences Furthermore, these questions could not be answered in a Yes-No format, and interviewees were required to provide detailed explanations for their answers to clarify their viewpoints Thus, the study could

access the participants' perspectives and gather high-quality information for the research

3.5 Data gathering procedure

The main data was collected through the model described below:

Figure 3 The process used in this study

The actual survey was conducted after consulting with supervising teachers and relevant studies, implemented from March 19, 2024, involving 46 English-Major Students at the Banking Academy The survey forms were distributed to students via platforms such as Facebook, Zalo, and Messenger to gather feedback

Figure 4 The four sections of developing the research’s survey

For qualitative data, the study collected information through semi-structured interviews with 5 English-Major Students at the Banking Academy However, only

4 students participated in the interviews, and 1 student declined to be interviewed due

to personal reasons

3.6 Data analysis

Before analyzing the data collected through the survey using various chart formats,

to ensure the reliability and accuracy of the survey table, several validation measures were undertaken Firstly, the survey table was sent to supervising teachers to verify the validity of the data, ensuring that the survey questions were meaningful and accurately reflected user experiences Subsequently, the data was further validated through Cronbach’s Alpha coefficient The value of Cronbach’s Alpha coefficientranges from [0;1] If the coefficients are higher than or equal to 0.7, it indicates high reliability of the variables and meets the study's requirements Conversely, if the Cronbach’s Alpha coefficient falls within the range of 0.95 or higher, the variablesare excluded from the survey table Finally, the data collected from the survey was analyzed using the Statistical Package for Social Sciences (SPSS) version 25, a tool commonly used in research to analyze numerical data, aiming to determine the relationships between variables in the data

First Section: Automated Essay Scoring (AES)

Second Section: The Chat GPT IELTS Writing Correction

The data collected from interviews was analyzed using a deductive approach combined with thematic analysis, focusing on validating and confirming the assumptions made initially, thereby producing appropriate and accurate research outcomes

CHAPTER 4: FINDINGS AND DISCUSSION 4.1 The survey data

4.1.1 Findings and Discussions of AES

Table 4.1 Levels of agreement or disagreement

Mean if Item

Deleted

Scale Variance if Item

Deleted

Corrected Item-Total Correlation

Cronbach's Alpha if Item Deleted

A1 Automated Essay

Scoring (AES) can be an

effective tool for IELTS

Writing skill Learners

A2 Immediate feedback is

a crucial aspect of AES

A3 In learning the IELTS

Writing Skill process,

using AES saves money

A4 In learning the IELTS

Writing Skill process,

using AES saves time

A5 In learning the IELTS

Writing Skill process, AES

can create for learners an

interactive environment

A6 Improving the IELTS

Writing Skill by using

AES is totally new to me

The table 4.2 illustrates correlation coefficients of variables within the factor

"English-Major Students’ perceptions towards using the Automated Essay Scoringcomplied with all requirements to be regarded as a reliable Likert Scale Firstly, Cronbach's Alpha coefficient for the variables in the table has a value of 0.824, which

is higher than 0.7 Lastly, all the values of the Corrected Item - Total Correlation exceeds the threshold of 0.3

Table 4.3 English-Major Students’ perceptions towards using the Automated EssayScoring

1 Automated Essay Scoring (AES) can be an effective tool for

IELTS Writing skill Learners

4.24 0.43 1

2 Immediate feedback is a crucial aspect of AES 4.15 0.51 2

3 In learning the IELTS Writing Skill process, using AES saves 3.80 0.72 4

4 In learning the IELTS Writing Skill process, using AES saves

time

3.87 0.65 3

5 In learning the IELTS Writing Skill process, AES can create

for learners an interactive environment

"In learning the IELTS Writing Skill process, AES can create for learners an interactive environment." with a mean value of 3.63 and SD of 0.77

Hence, the data table indicates that the average of English-Major students’ perceptiontowards AES is 3.75 According to the agreement or disagreement levels shown in Table 4.1, students' acceptance of AES is high

The acceptance of English-Major students towards the effectiveness of AES is relatively high, which can be attributed to these tools often offering immediate feedback on their essays, then helping them improve their IELTS writing skills Through their experiences with this tool, students feel optimistic during the learning process and more accepting of AES However, the majority of them don't believe that using AES is completely new to them as in the quickly evolving world of information