AI-Augmented Note-Taking for Supporting EFL Learners in Higher Education Contexts

* * * On the Internet * * *

May 2026 — Volume 30, Number 1

https://doi.org/10.55593/ej.30117int1

Joe Terantino
Oklahoma State University, USA
<joe.terantinookstate.edu>

Sidra Zaheer
Oklahoma State University, USA
<szaheerokstate.edu>

Yimeng Zhu
Oklahoma State University, USA
<yimeng.zhuokstate.edu>

Abstract

Note-taking in English as a foreign language (EFL) contexts has transformed significantly from traditional pen and paper formats to encompass more digital applications, including a wide array of Artificial Intelligence (AI) note-taking tools. As AI note-taking becomes a more prominent strategy for EFL learners, its rapid growth introduces new pedagogical and ethical complexities that educators must address. We conceptualize AI note-taking applications as mediational tools that shape and extend learners’ cognitive and linguistic development. By providing real-time transcription, translation, and contextual definitions of difficult and unfamiliar words or phrases, AI tools scaffold listening comprehension and reduce the cognitive load of manual note-taking, which allows learners to focus more on active listening and comprehension. This article proposes a four-phase, instructional model grounded in Sociocultural Theory for implementing AI-augmented note-taking with EFL learners in higher education. We conclude by discussing pedagogical implications for integrating AI note-taking to sustain active participation and foster learners’ movement toward greater autonomous note-taking and comprehension.

Keywords: artificial intelligence, digital note-taking, English as a foreign language, mediation, multilingual learners, sociocultural theory

In a university American History class, Lee, an international student from China, struggled to follow a lecture on the Civil Rights Movement. When the professor mentioned the “Little Rock Nine,” Lee was unfamiliar with the term, unlike his peers who easily connected it to prior knowledge. Searching for answers on his phone, Lee split his attention between the lecture and online resources. Though he eventually learned that the Little Rock Nine were the first African American students to integrate into Central High School in 1957, he missed the professor’s transition to the Civil Rights Act of 1964, leaving his notes and understanding of the new content incomplete.

Reframing Note-Taking in the Age of AI

Similar to the example described above, English as a Foreign Language (EFL) learners across the globe frequently encounter significant obstacles when it comes to note-taking in educational settings where lessons are delivered in English, often their second or third language, and embedded within a different cultural context. This linguistic and cultural gap can impede their ability to process and record information effectively. For example, listening comprehension during university lectures, discussions, or watching videos can be daunting due to struggles with understanding complex academic vocabulary and content-specific jargon (Hellekjær, 2010), or idiomatic expressions and key cultural concepts (Al-Khresheh, 2020), which are integral to their coursework and development of content-specific knowledge and skills. In addition, their comprehension of such oral inputs may be hindered by varying accents, rapid speech, and cultural differences in communication styles (Purwanto et al., 2021). Ongoing challenges with listening comprehension often lead to a general lack of confidence that ultimately impacts academic performance (Prastiyowati, 2019) if adequate support is not provided.

The benefits of using note-taking as a strategy to optimize student learning in these contexts have been well documented in previous research including increased comprehension, information retention, and overall academic performance (Jansen et al., 2017; Salame & Thompson, 2020). More specifically, in the context of EFL learners, note-taking has been linked with improved comprehension and retention but also with improvements in vocabulary acquisition (Ahmadi Safa & Rozati, 2017; Jin & Webb, 2024). Many educators have introduced students to structured note-taking methods, such as outlining, which often helps to reduce the cognitive load required of the learners by organizing information and emphasizing important concepts (Jansen et al., 2017). Research with collaborative note-taking strategies, where learners share the responsibility to take notes, has yielded similar results, highlighting the shared cognitive load and increased comprehension of the learners (Costley & Fanguy, 2021). Collectively, this research documenting the various benefits of note-taking on the learning process supports the idea of continuing with an emphasis on note-taking in all educational contexts.

More recently, Artificial Intelligence (AI)-powered note-taking tools have transformed the way we are able to gather and organize information (Saini et al., 2023). Evolving from traditional forms of learner-generated notes, whether taken with pen and paper or digital note-taking via typing or stylus pen, AI interactive note-taking tools offer features like text-to-speech, instant translation, and automatic summaries. Further, research has demonstrated that language models that power AI tools can provide instant translations and explanations of unfamiliar terms that assist multilingual learners to overcome vocabulary barriers in real-time (Ayyaz, 2025). Yet, within education, the use of AI note-taking and related research is still emerging. Therefore, this article outlines a four-phase, instructional model, grounded in Sociocultural Theory (SCT) (Vygotsky, 1978), for implementing AI-augmented note-taking, harnessing its mediational power to support guided learning activities and social interactions for EFL learners in higher education.

Challenges for EFL Learners

As EFL students engage in academic learning, whether in English classes in their home countries or at universities in English-speaking countries, they often encounter a range of linguistic and cultural challenges that may hinder their progress and engagement (Purwanto et al., 2021). One of the most immediate obstacles is listening comprehension. Lectures, seminars, and group discussions often feature speakers with varied accents, speech rates, and discourse styles. For students who have primarily been exposed to only one variety of English, such as American or British English, this variation can be disorienting. As a result, they may struggle to follow along, retain key points, or take effective notes in real time (Purwanto et al., 2021). Multilingual learners, in particular, tend to exhibit reduced working memory capacity when processing auditory input in their second language, which further exacerbates comprehension difficulties (Siegel, 2022).

The issue is not merely about vocabulary, but also about the cognitive burden of simultaneously decoding speech, organizing content, and recording relevant information. This cognitive load becomes especially pronounced in fast-paced academic environments, where students are expected to identify main ideas, distinguish relevant from irrelevant points, and transcribe accurate notes while interpreting complex language (Jansen et al., 2017; Siegel, 2022). A study conducted at an English-medium instruction university in Turkey revealed that EFL learners frequently struggled to keep up with lectures that moved quickly or incorporated dense, discipline-specific terminology without adequate explanation (Kamaşak et al., 2021). The outcome was often incomplete or fragmented note-taking, which left students with little to build upon when completing assignments.

In addition to listening difficulties, EFL learners face considerable challenges when it comes to navigating the specialized vocabulary and syntactic structures characteristic of academic discourse. Educational settings often rely heavily on abstract, technical, and context-specific language that is rarely used in conversational English. As Nushi and Orouji (2020) point out, without a strong grasp of these linguistic features, students risk misunderstanding central ideas within the course content. Despite progress in mastering general academic English, many EFL students continue to struggle with idiomatic expressions and culture-specific references that feature metaphors, phrasal verbs, and figurative speech (Benattabou, 2020). In Afghanistan, undergraduate EFL students recognized the importance of learning idioms but lacked the cultural grounding to interpret them accurately (Orfan, 2020). A similar study conducted in Indonesia found that students frequently confused idiomatic expressions with literal phrases, resulting in misinterpretation or complete breakdowns in comprehension (Anjarini & Hatmanto, 2021), because they often lack the necessary cultural frames of reference to successfully interpret idiomatic expressions.

These challenges, including listening comprehension, academic vocabulary, idiomatic usage, and cultural references, are not isolated. They interact and compound each other, often leaving learners cognitively overwhelmed. In settings where these challenges remain unaddressed and where educators lack the time, training, or resources to intervene, students are often left unsupported. AI-powered note-taking tools present a timely and scalable opportunity to assist EFL learners by capturing and organizing spoken content, simplifying academic vocabulary, highlighting idiomatic expressions, and enabling learners to review material at their own pace. In doing so, AI note-taking tools may offer a form of scaffolding that complements human instruction, especially in linguistically diverse and fast-paced academic environments. In the following section, we explore how such tools can be thoughtfully leveraged to support the needs outlined here.

How AI Note-Taking Tools Function

AI note-taking tools leverage artificial intelligence through a complex set of operations including Natural Language Processing and Advanced Speech Recognition that enable the applications to accurately and contextually transfer spoken words, either in real-time or in pre-recorded speeches, into text-based notes. Figure 1 depicts the general process that occurs as AI note-taking tools capture input from various sources, including live lectures, recorded lectures, and other video inputs, and transform this content into meaningful and comprehensible outputs for EFL learners.

Figure 1. Overview of the AI Note-Taking Process

As shown above, the first operation in such note-taking is referred to as audio capture and pre-processing which involves the filtering of environmental noise as well as improving the clarity of speech. This is important in classrooms where ambient noise, multiple speakers, and changing audio quality pose challenges. The second operation involves the application of deep learning models that have been trained using large amounts of multilingual datasets. These speech recognition models differentiate accents, speech rates, and language variations. Third, they break input into meaningful parts and identify key concepts and contextual relationships. Built-in translation models offer instant translation, while semantic analysis tools identify and explain cultural references or idiomatic expressions that may be unfamiliar to EFL students. Finally, AI organizes the processed information into searchable notes enhanced with recommendations for additional learning materials. For example, as illustrated in Figure 2, the EasyNoteAI tool converted a two-minute recorded lecture about how volcanoes erupt into a detailed mind map. This visual representation connects key ideas from the video to organize the information in a meaningful way for the learner.

Figure 2. AI Note-Taking Tool: EasyNoteAI

Beyond basic transcription, AI note-taking tools employ advanced Natural Language Processing algorithms to analyze and structure the information meaningfully. The tools break down the input, identify context, and create categories and understandable sections or searchable tags that allow learners to search for specific notes later, based on context or keywords. They can also summarize, highlight the important points, or develop visual representations (such as a mind map or concept network map). The adaptive nature of AI tools allows them to integrate with learning management systems and digital textbooks.

Figure 3 illustrates some of these key functions by displaying the user interface for QuickTakes. The multi-functional toolbar at the top of the screen includes several integrated learning tools accessible through different tabs: Outline, Flashcards, Study Guide, Glossary, Practice, Videos, Transcript, and Chat. The main content area shows an outline from a course lecture on “The Boston Tea Party: Catalyst for Revolution,” with clear hierarchical organization using headers and bullet points for subtopics like Introduction, Background, Motivations, The Act of Protest, and The Tea Act of 1773. The integration of both study aids, like flashcards and practice questions, and chat-based communication tools makes QuickTakes a more comprehensive note-taking platform.

Figure 3. AI Note-Taking Tool: QuickTakes

The Mediational Power of AI Note-Taking Tools

In recent years, the role of AI in education has shifted from automation to actively supporting how learners engage with, interpret, and internalize new knowledge. To examine the mediational potential of AI-powered note-taking tools in EFL contexts, this section draws on SCT, a framework originating from the work of Vygotsky (1978) and further developed by scholars such as Wertsch (1991), Lantolf (2000), and Zhou (2020). SCT offers a foundational lens through which the integration of AI in learning can be understood as a form of mediated activity, particularly relevant for linguistically diverse learners in cognitively demanding academic settings.

Framed through SCT, the learning process begins with interaction in socially and culturally meaningful contexts, where tools, including language, texts, and digital technologies, mediate access to knowledge (Wertsch, 1991). This mediation enables scaffolding, wherein learners receive structured and responsive support that helps them engage with tasks slightly beyond their current competence (Wood et al., 1976). These scaffolded interactions occur within the Zone of Proximal Development (ZPD) (Vygotsky, 1978), a space where learners’ potential is optimized through guided participation. While such guidance has traditionally been offered by teachers or peers, contemporary research has shown that AI technologies can now serve as adaptive mediators by offering timely and context-sensitive support, especially when immediate human assistance is unavailable (Lantolf & Poehner, 2014; Liu, 2025). As learners revisit concepts, apply strategies, and develop familiarity through continued interaction, they gradually internalize the knowledge and the cognitive strategies used to construct it (Lantolf & Thorne, 2006). Over time, this leads to reduced reliance on external assistance and increased autonomy, as students begin to self-regulate their learning in complex academic environments (Alharbi, 2023).

In this context, AI-powered tools such as note-taking applications act as intelligent mediators within the learner’s ZPD. By offering real-time feedback, clarifying abstract content, and enabling flexible, repeated engagement with academic material, they support learners in moving from scaffolded assistance toward independent meaning-making. Tools such as Otter, EasyNoteAI, and QuickTakes convert lectures into real-time text, organize content into thematic structures, and allow learners to annotate, revisit, and reflect on complex material at their own pace. These actions facilitate both externalization and internalization, which enables learners to first capture academic input and then gradually integrate it into their evolving language and content knowledge (Lantolf & Thorne, 2006). Moreover, by adapting to learners’ linguistic and cognitive needs, these tools provide a personalized form of mediation that aligns closely with the learner’s ZPD and makes them well-suited for supporting academic success in multilingual, cognitively demanding environments.

Instructional Model for AI-Augmented Note-Taking

In this section, drawing from an SCT perspective, we delineate an instructional model for implementing AI-augmented note-taking that emphasizes planning for mediation in curriculum design, guided practice, social interaction, and resynthesis of AI-generated notes. We focus on EFL learners in higher education because they face an intense cognitive load while processing complex academic content in a second language with limited support. International students, often studying in English-speaking universities, are expected to perform independently while also navigating unfamiliar vocabulary, fast-paced lectures, and culturally specific references. Figure 4 outlines our step-by-step approach, which aims to move the learner from other-regulated to self-regulated, and the subsequent sections explain each step in further detail.

Figure 4. AI-Augmented Note-Taking and the ZPD

Phase 1: Planning for Mediation in Curriculum Design

In Phase 1, the educator positions AI note-taking not as an add-on but as a mediational tool to be meaningfully integrated into curriculum design. Planning should begin with an analysis of the lesson’s discourse demands, including the density of specialized terminology, abstract concepts, and culturally embedded references. This information guides the teacher’s choice of an AI note-taking platform suited to the subject matter and the learners’ proficiency levels. Strategically selecting the tool best aligned with their proficiency level can significantly improve comprehension, organization, and engagement (Zhang et al., 2025). Therefore, EFL educators and learners need to consider which AI note-taking tool best suits their unique needs.

Appendix A highlights some of the most widely used AI note-taking tools and their defining characteristics. For example, beginning-level EFL learners might utilize platforms such as NotebookLM and NotionAI, because they stand out for their multilingual, user-friendly interfaces. Students can begin with simple lecture summaries or vocabulary logs, then gradually expand into more complex outputs such as categorized notes or linked ideas. For advanced-level EFL students, Otter and EasyNoteAI offer more sophisticated features for code-switching and translation that align with the needs of advanced learners who will process complex academic content. For students in hybrid or online learning formats, Zoom IQ and Otter are designed to capture synchronous online discussions, breakout room conversations, and virtual presentations. For students who prefer the tactile experience of handwriting, GoodNote6 offers an effective hybrid solution. Its handwriting recognition and searchable interface combine the cognitive benefits of longhand note-taking with the organization of digital storage. Some research confirms that handwriting notes supports deeper encoding of information for learners compared to typing (Mueller & Oppenheimer, 2014). Last, for research-focused graduate students, Obsidian and NotionAI offer advanced organizational features that enable graduate students to handle large amounts of complex research materials by creating detailed concept maps, research outlines, and interconnected note networks.

From a sociocultural perspective, embedding AI note-taking tools into curriculum design means treating them as cultural artifacts that mediate access to disciplinary discourse. The educator deliberately structures activities where students must interact with AI-generated notes to clarify, question, and reorganize them, ensuring that note-taking becomes an active, dialogic process rather than a passive reception of machine output. For this purpose, students might compare AI notes to their own hand-written summaries, collaboratively edit AI transcripts for clarity, or use highlighted key terms to negotiate shared conceptual understanding. In this way, planning for mediation shifts the role of AI from mere transcription toward fostering higher-order thinking, enabling learners to engage with disciplinary knowledge while developing strategies for independent meaning-making.

Phase 2: Guided Practice

Research in second language acquisition emphasizes that guided practice is most effective when learners receive comprehensible input and opportunities to notice target language features (Swain, 2005; VanPatten, 2015). AI note-taking tools can help to achieve this by automatically generating lecture summaries, vocabulary glossaries, and key concept lists that serve as scaffolds for subsequent practice activities. They are especially helpful in improving listening comprehension during lectures, group discussions, or video-based learning, because they alleviate the burden of simultaneously listening and note-taking. These tools allow EFL learners to direct their cognitive resources toward comprehending and processing the content itself (Siegel, 2022). This automation acts as a mediational tool, a core concept of Vygotsky’s SCT (1978), by supporting learners’ abilities to engage more fully with academic content by offloading peripheral cognitive tasks. This is crucial because prior research indicates that EFL learners often face elevated cognitive demands while processing real-life spoken academic input (Jansen et al., 2017).

AI-generated notes can serve as input for a variety of guided output activities that build fluency and accuracy. For example, in an environmental science lecture on climate change, the AI-generated notes include a summary such as, “Global temperatures are rising due to increased greenhouse gas emissions, primarily carbon dioxide from burning fossil fuels.” The instructor can transform this into a cloze activity by removing key terms (temperatures, greenhouse gas emissions, carbon dioxide, fossil fuels) and asking students to reconstruct the sentence using contextual clues and their prior knowledge. This activity reinforces accurate use of technical vocabulary while consolidating students’ understanding of cause-and-effect relationships in the content. Similarly, in a history course covering the French Revolution, the AI-generated notes provide several sentences: “Economic hardship increased resentment toward the monarchy. The storming of the Bastille became a symbol of the French Revolution’s resistance. Enlightenment ideas inspired calls for equality.” The instructor could shuffle these sentences and ask students to arrange them into a logical order that reflects the historical sequence and thematic coherence. Students then expand the reordered notes into a full paragraph, integrating transition words such as first, as a result, and ultimately. This guided output task helps learners practice discourse organization and academic writing while deepening their grasp of historical content.

Phase 3: Social Interaction and Dialogic Learning

AI-generated notes can serve as powerful social artifacts that mediate learning within the ZPD by supporting collaborative knowledge construction. In EFL contexts, these tools create opportunities for dialogic learning, as students engage with shared AI-produced texts to negotiate meaning, question interpretations, and co-construct understanding. Grounded in SCT, such interactions exemplify how technology can act as a mediational tool to scaffold learners’ movement from assisted to independent performance. Rather than replacing human interaction, AI-generated notes extend the social space of learning to transform individual comprehension challenges into opportunities for collective inquiry, reflection, and internalization of higher-order thinking.

Within the context of social interaction and dialogic learning, teachers can design activities that position AI note-taking tools as a starting point for collaborative meaning-making rather than an endpoint. One practical suggestion is to have students work in pairs or small groups to compare their own notes with the AI-generated version, discussing discrepancies, clarifying misunderstood terms, and jointly deciding which information is most relevant. This negotiation of meaning transforms note comparison into a dialogic activity that strengthens comprehension and critical thinking. Another approach is to facilitate peer-led discussions where students use AI-generated summaries as prompts for debate, role-play, or problem-solving tasks. For example, in a political science class, AI-generated notes on a lecture about democratic systems could be used to prompt group debates on how these systems function in different cultural contexts. Instructors might also ask students to co-edit AI transcripts in real time, collaboratively paraphrasing or annotating key sections to ensure accuracy and deepen conceptual understanding. In these ways, when students exchange their AI-generated notes in pairs or small groups, they engage in what researchers refer to as collective scaffolding, in which learners use meaningful interaction to assist each other’s linguistic development and content-based learning. While AI tools enhance engagement through immediate feedback and personalized practice, research confirms that peer interaction remains essential for providing socioemotional benefits and sustained meaningful engagement in classroom settings (Lee, 2025).

Phase 4: Re-synthesizing Understanding for Self-Regulated Learning

As instruction evolves beyond guided support, learners begin to re-engage with AI-generated notes in ways that promote deeper conceptual understanding and strategic reflection. Through a SCT lens, this phase marks the learner’s gradual shift from externally mediated learning to internally regulated thinking, where students transform prior scaffolding into personal, transferable strategies (Vygotsky, 1978; Lantolf & Thorne, 2006).

Here, re-synthesis involves more than repeating or summarizing previous material; it invites learners to critically examine what they understood, how they came to understand it, and how they might re-organize their knowledge. Educators facilitate this process by prompting students to revisit and refine their notes, both AI-generated and peer-reviewed. Learners are then encouraged to question the completeness of the information, identify any shortcomings, and integrate multiple perspectives. For instance, in a graduate-level Sociology course, students analyzing Edward Said’s Orientalism may begin with AI-generated summaries that contain surface-level renderings of complex ideas, but during re-synthesis, the teacher invites learners to pose questions such as, “How did your understanding of cultural hegemony shift after discussing it with peers? What key terms or metaphors did the AI overlook, and why might those be important? How would you explain this concept to a peer from another discipline?” These prompts encourage metacognitive engagement and bridge the gap between AI-generated output and human meaning-making by pushing learners to develop a nuanced, more accurate and strategically refined response.

As learners re-engage with content through critical reflection, autonomy begins to emerge as a natural extension of the dialogic, collaborative processes fostered in earlier phases. Instructors can then reframe earlier collaborative activities as tools for internalization, signaling to students that these same tools can now support more independent forms of learning as described in the following:

• Think-Pair-Report shifts from information-sharing to meaning reconstruction. Students begin by individually identifying unclear or inaccurate segments in their summaries, pair with a peer to negotiate meaning, and finally report revised understandings to the group. The movement from passive correction to intentional re-framing highlights deeper cognitive engagement and growing autonomy.
• Summarize and Share enables learners to co-construct key takeaways but now with a more critical lens, deciding not only what to keep from AI notes, but why it matters and how to best represent it in their own words.
• Student-Generated Discussion Prompts represent an evolved metacognitive orientation. Instead of responding to teacher-directed cues, students pose their own questions drawn from their notes, identifying gaps, contradictions, or areas needing further inquiry. For example, “Why does the AI summary miss the satirical tone used in the lecture?” or “How does this concept relate to what we learned last week?”

These activities are not just relative practice exercises, they are tangible markers of internalization and moments where students begin to self-direct their learning while actively engaging in reflection, synthesis, and knowledge construction. They help learners to move beyond reliance on AI outputs or teacher feedback by developing the internal frameworks needed to critically assess and build upon academic input, thus leading towards autonomy.

Throughout this process, learners also come to recognize the limitations of AI, such as missed nuances or misinterpreted metaphors, which can be presented as opportunities for human intervention and conceptual refinement. These moments prompt learners to draw on both social interaction and personal insight, deciding when to trust the tool, when to seek clarification, and how to reconstruct knowledge in their own words. This growing awareness is key to internalization. It leads learners to monitor their learning habits, evaluate their cognitive strategies, and choose the most effective paths forward, depending on task complexity and language demands.

Ultimately, this phase illustrates that autonomy does not emerge in isolation. It is cultivated through recursive, dialogic learning, which is first scaffolded by peers and teachers, later mediated by AI, and finally internalized as learners develop the ability to reflect, evaluate, and act strategically.  When students revisit how their thinking has evolved, collaboratively refine their understanding, and plan future learning with intention, they demonstrate true academic autonomy which is built through the combined mediational forces of AI, peer support, and instructional guidance (Lantolf & Poehner, 2014; Alharbi, 2023).

Conclusion

In conclusion, AI note-taking tools have the potential to revolutionize educational practices, particularly for EFL learners who often need additional scaffolding for increasing their listening comprehension. However, to harness their full potential, thoughtful implementation is essential, especially one that considers equitable access, accuracy, and active engagement. Equitable access is the foundational step. Marginalized students risk exclusion without access to devices like tablets, laptops, or reliable internet, which are necessary for operating AI tools. Providing these resources in underfunded areas is critical to prevent further exacerbating the digital divide. At the same time, educators must balance the benefits of AI note-taking tools with the risks of over-reliance. While AI can streamline note-taking, it should complement—not replace—active learning practices to build essential skills like critical thinking, language development, and engagement with content.

For multilingual learners, navigating AI tools with multiple features can be overwhelming. To mitigate this, educators should provide targeted instruction, focusing on specific functions such as transcription, summarization, or keyword highlighting. This step-by-step approach enables students to use these tools effectively without feeling overburdened (Sajja et al., 2024). Furthermore, verifying the accuracy and reliability of AI-generated outputs is crucial. Notes, translations, and summaries should be cross-checked for cultural relevance and correctness to avoid potential misunderstandings. This fosters digital literacy by teaching learners to critically evaluate the information they consume.

Beyond these practical considerations, AI-generated notes can act as mediational tools that support learners’ movement within their ZPD. By transforming language input into accessible, revisable artifacts, these tools enable learners to revisit, analyze, and collaboratively build understanding with peers and instructors. When used interactively, AI notes become shared reference points that scaffold comprehension and promote dialogic learning, turning individual challenges into opportunities for co-constructed meaning. Such thoughtful integration ensures that AI is not just a technological add-on but a mediational resource that enhances the process and experience of learning.

About the Authors

Joe Terantino is an associate professor of second language education in the School of Teaching, Learning & Educational Sciences at Oklahoma State University. His research explores the intersection of second language acquisition, curriculum and instruction, and teacher education, with particular attention to multilingual learners and the role of artificial intelligence and other instructional technologies. ORCID ID: 0000-0002-3552-4993

Sidra Zaheer is a doctoral student in Literacies and Language Arts Education at Oklahoma State University. Her research examines how multilingual learners engage with generative AI, digital literacies, and young adult literature as sites for developing critical literacy and academic writing. ORCID ID: 0000-0002-1387-4204

Yimeng Zhu is a doctoral student in Literacies and Language Arts Education at Oklahoma State University. His scholarly work investigates the implementation and pedagogical implications of artificial intelligence and emerging technologies in English as a Foreign Language contexts. ORCID ID: 0009-0000-8888-9040

To Cite this Article

Terantino, J., Zaheer, S., & Zhu, Y. (2026). AI-Augmented note-taking for supporting EFL learners in higher education context.  Teaching English as a Second Language Electronic Journal (TESL-EJ), 30(1). https://doi.org/10.55593/ej.30117int1

References

Ahmadi Safa, M. A., & Rozati, F. (2017). The impact of scaffolding and nonscaffolding strategies on the EFL learners’ listening comprehension development. The Journal of Educational Research, 110(5), 447–456. https://doi.org/10.1080/00220671.2015.1118004

Alharbi, W. (2023). AI in the foreign language classroom: A pedagogical overview of automated writing assistance tools. Education Research International, 1, 1-15. https://doi.org/10.1155/2023/4253331

Al-Khresheh, M. H. (2020). The impact of cultural background on listening comprehension of Saudi EFL students. Arab World English Journal, 11(3), 349- 371. https://doi.org/10.24093/awej/vol11no3.22

Anjarini, R. D., & Hatmanto, E. D. (2021). Challenges and strategies in understanding English idioms: English as a foreign language students’ perception. In International Conference on Sustainable Innovation Track Humanities Education and Social Sciences (ICSIHESS 2021) (pp. 241-247). Atlantis Press. https://doi.org/10.2991/assehr.k.211227.039

Ayyaz, S. (2025). AI translation tools in language learning: Bridging gaps and enhancing skills. In M. M. Ali, M. N. Anwar, S. Fazal, & S. Ayyaz (Eds.), AI Applications for English language learning (pp. 43-72). IGI Global Scientific Publishing.

Benattabou, D. (2020). On the teaching and learning of culture-loaded words: The case of Moroccan EFL learners. International Journal of Linguistics and Translation Studies, 1(3), 1-19. https://doi.org/10.36892/ijlts.v1i3.62

Costley, J., & Fanguy, M. (2021). Collaborative note-taking affects cognitive load: the interplay of completeness and interaction. Educational Technology Research and Development, 69, 655-671. https://doi.org/10.1007/s11423-021-09979-2

Hellekjær, G. O. (2010). Lecture comprehension in English-medium higher education. HERMES-Journal of Language and Communication in Business, 45, 11-34. https://doi.org/10.7146/hjlcb.v23i45.97343

Jansen, R. S., Lakens, D., & IJsselsteijn, W. A. (2017). An integrative review of the cognitive costs and benefits of note-taking. Educational Research Review, 22, 223-233. https://doi.org/10.1016/j.edurev.2017.10.001

Jin, Z., & Webb, S. (2024). The effectiveness of note taking through exposure to L2 input: A meta-analysis. Studies in Second Language Acquisition, 46(2), 404-426. https://doi.org/10.1017/s0272263123000529

Kamaşak, R., Sahan, K., & Rose, H. (2021). Academic language-related challenges at an English-medium university. Journal of English for Academic Purposes, 49, 1-16. https://doi.org/10.1016/j.jeap.2020.100945

Lantolf, J. P. (Ed.). (2000). Sociocultural theory and second language learning. Oxford University Press.

Lantolf, J. P., & Poehner, M. E. (2014). Sociocultural theory and the pedagogical imperative in L2 education: Vygotskian praxis and the research/practice divide. Routledge.

Lantolf, J. P., & Thorne, S. L. (2006). Sociocultural theory and the genesis of second language development. Oxford University Press.

Lee, J. (2025). EFL adolescents’ engagement in artificial intelligence and peer interaction. Language Learning & Technology, 29(1), 1-21. https://doi.org/10.64152/10125/73643

Liu, X. (2025). Reconceptualizing foreign language learning through artificial intelligence within the framework of the zone of proximal development. GBP Proceedings Series, 8, 9-15. https://ideas.repec.org/a/axf/gbppsa/v8y2025ip9-15.html

Mueller, P. A., & Oppenheimer, D. M. (2014). The pen is mightier than the keyboard: Advantages of longhand over laptop note taking. Psychological Science, 25, 1159–1168. https://doi.org/10.1177/0956797614524581

Nushi, M., & Orouji, F. (2020). Investigating EFL teachers’ views on listening difficulties among their learners: The case of Iranian context. Sage Open, 10(2). https://doi.org/10.1177/2158244020917393

Orfan, S. N. (2020). Afghan EFL students’ difficulties and strategies in learning and understanding English idioms. Cogent Arts & Humanities, 7(1), 1-13. https://doi.org/10.1080/23311983.2020.1796228

Prastiyowati, S. (2019). Anxiety on students’ listening comprehension in university students in Malang. Celtic: A Journal of Culture, English Language Teaching, Literature and Linguistics, 6(1), 65-77. https://doi.org/10.22219/celtic.v6i1.8758

Purwanto, D., Fadhly, F. Z., & Rahmatunisa, W. (2021). Listening comprehension study: Difficulties and strategies used by college students. Indonesian Journal of Learning and Instruction, 4(1), 55-62. https://journal.uniku.ac.id/index.php/IJLI/article/view/4345

Saini, M., Arora, V., Singh, M., Singh, J., & Adebayo, S. O. (2023). Artificial intelligence inspired multilanguage framework for note-taking and qualitative content-based analysis of lectures. Education and Information Technologies, 28(1), 1141-1163. https://doi.org/10.1007/s10639-022-11229-8

Sajja, R., Sermet, Y., Cikmaz, M., Cwiertny, D., & Demir, I. (2024). Artificial intelligence-enabled intelligent assistant for personalized and adaptive learning in higher education. Information, 15(10), 1-23. https://doi.org/10.3390/info15100596

Salame, I. I., & Thompson, A. (2020). Students’ views on strategic note-taking and its impact on performance, achievement, and learning. International Journal of Instruction, 13(2), 1–16. https://doi.org/10.29333/iji.2020.1321a

Siegel, J. (2022). Factors affecting notetaking performance. International Journal of Listening, 38(2), 118–130. https://doi.org/10.1080/10904018.2022.2059484

Swain, M. (2005). The output hypothesis: Theory and research. In E. Hinkel (Ed.). Handbook of research in second language teaching and learning (pp. 471-483). Routledge.

VanPatten, B. (2015). Foundations of processing instruction. International Review of Applied Linguistics in Language Teaching, 53(2), 91-109. https://doi.org/10.1515/iral-2015-0005

Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press

Wertsch, J. V. (1991). Voices of the mind: A sociocultural approach to mediated action. Harvard University Press.

Wood, D., Bruner, J. S., & Ross, G. (1976). The role of tutoring in problem solving. Journal of Child Psychology and Psychiatry, 17(2), 89–100. https://doi.org/10.1111/j.1469-7610.1976.tb00381.x

Zhang, W., Nie, H., Fan, J., & Liu, H. (2025). Exploring the dynamics of artificial intelligence literacy on English as a foreign language learners’ willingness to communicate: The critical mediating roles of artificial intelligence learning self-efficacy and classroom anxiety in EFL education. Behavioral Sciences, 15(4), 1-15. https://doi.org/10.3390/bs15040523

Zhou, Z. (2020). Exploring AI as a tool for mediating academic language learning: A sociocultural perspective. Journal of Physics: Conference Series, 1646(1), 1-5. https://doi.org/10.1088/1742-6596/1646/1/012142

Appendix A

Overview of AI Note-Taking Tools

Copyright of articles rests with the authors. Please cite TESL-EJ appropriately. Editor’s Note: The HTML version contains no page numbers. Please use the PDF version of this article for citations.