CoChat
Sign Up
Cited by 80Artificial Intelligence in EducationAI in Service InteractionsIntelligent Tutoring Systems and Adaptive Learning

Implementing the bashayer chatbot in Saudi higher education: measuring the influence on students' motivation and learning strategies

Open access
Al-Abdullatif, Ahlam Mohammed, Al-Dokhny, Amany Ahmed, Drwish, Amr Mohammed·2023·Frontiers in Psychology
DOI 10.3389/fpsyg.2023.1129070PMC PMC10226531
Open this paper in CoChat — free accountOpen PDF

Abstract

Since the fourth industrial revolution, intelligent software and applications that attempt to mimic human behavior have become increasingly common. The chatbot is an example of an artificial intelligence-based computer program that simulates human behavior by having a conversation and interacting with users using natural language. The implementation of chatbot technology in the educational context is still in its nascent stage, and further investigation into measuring its effectiveness in supporting learning and teaching processes is required, particularly in the context of higher education. Thus, this study presents the design and implementation of a task-oriented chatbot, that is embedded into the WhatsApp application, called Bashayer. It aims at supporting postgraduate students' motivation and learning strategies in Saudi Arabia. A quasi-experimental design with a single-subject experimental approach was adopted with a sample of 60 Saudi postgraduate students. The descriptive analysis of the collected data showed promising results of postgraduate students utilized the Bashayer chatbot system. Participants in the experimental group that used Bashayer were more motivated to learn than those in the control group. Participants also practiced more cognitive and metacognitive learning strategies while utilizing the chatbot compared to the control group. The results of this study are encouraging for the development of chatbot systems similar to Bashayer to support postgraduate students' successful learning. These results contribute to bridging the research gap and adding to the literature on chatbots use in postgraduate educational contexts.

AI snapshot

Written from the paper’s full text.

TL;DR

This study designed and implemented Bashayer, a task-oriented chatbot embedded in WhatsApp, to support Saudi postgraduate students’ motivation and learning strategies. A quasi-experimental comparison found that students who used Bashayer reported significantly higher task value, self-efficacy, cognitive learning strategies, and metacognitive self-regulation than a control group.

Key findings

  • The experimental group scored higher than the control group on motivation: task value 4.08 vs. 3.38 (t = 6.64, p < 0.05), self-efficacy 3.99 vs. 3.37 (t = 4.33, p < 0.05), and total motivation 4.03 vs. 3.34 (t = 6.25, p < 0.05).
  • The experimental group also scored higher on learning strategies: cognitive strategies 4.11 vs. 3.33 (t = 7.18, p < 0.05), metacognitive self-regulation 3.97 vs. 3.25 (t = 6.07, p < 0.05), and total learning strategies 4.04 vs. 3.29 (t = 6.89, p < 0.05).
  • Pre-test homogeneity was confirmed: no statistically significant difference between groups (t = 0.097, p > 0.05), with control M = 12.83, SD = 2.704 and experimental M = 12.76, SD = 2.608.
  • The paper concludes that Bashayer positively influenced postgraduate students’ motivation and cognitive/metacognitive learning strategies.

Methods

  • Quasi-experimental design with a single-subject experimental approach; sample of 60 Saudi postgraduate students in the Master of Educational Technologies program at King Faisal University, enrolled in two courses during the first semester of 2022–2023.
  • Participants were divided into 30 experimental students taught online using Bashayer via WhatsApp/Freshdesk and 30 control students taught via traditional face-to-face mode; a separate pilot sample of 10 was used for instrument validation.
  • The Motivated Strategies for Learning Questionnaire (MSLQ; Pintrich, 1991) was used pre- and post-test, with 38 items on a 5-point Likert scale; analysis used descriptive statistics and independent samples t-tests in IBM SPSS v.26.

Limitations

  • The paper states that the small sample of 60 postgraduate students limits generalizability, that the courses were theoretical and results may differ in applied disciplines, and that the one-semester duration may introduce novelty or single-semester bias.
  • The paper also states methodological and technical limitations: reliance on quantitative MSLQ data only, no qualitative data; database limitations meant Bashayer could not always answer all queries; and the design was limited to basic cognitive skills (remembering, understanding, organizing) and metacognitive control/self-regulation rather than complex strategies such as reasoning and problem-solving.
  • Evident from the text: outcomes rely on self-reported MSLQ responses, and the study was conducted in one institution and program, which further constrains broader claims beyond the stated sample and context.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3389/fpsyg.2023.1129070

Cites

71 of 71 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 49 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    Participants practiced more cognitive and metacognitive learning strategies while utilizing the chatbot compared to the control group.

    “Participants also practiced more cognitive and metacognitive learning strategies while utilizing the chatbot compared to the control group.”
    Quote in the paperSubstantial claim
  • Findingown data

    Participants in the experimental group that used Bashayer were more motivated to learn than those in the control group.

    “Participants in the experimental group that used Bashayer were more motivated to learn than those in the control group.”
    Quote in the paperSubstantial claim
  • Findingown data

    Postgraduate students' mean task value response was 0.7 greater in the experimental group (4.08) than in the control group (3.38).

    “As shown in Table 3, postgraduate students' mean response for task value was 0.7 greater in the experimental group (4.08) than the control group (3.38).”
    Quote in the paperSubstantial claim
  • Findingown data

    The experimental group's total MSLQ motivation scale mean (4.03) was 0.7 greater than the control group's (3.34).

    “In terms of the MSLQ motivation scale in total, the students from the experimental group (M = 4.03) showed 0.7 greater level of motivation than their peers in the control group (M = 3.34).”
    Quote in the paperSubstantial claim
  • Findingown data

    The experimental group's total MSLQ learning strategies scale mean (4.04) was 0.8 higher than the control group's (3.29).

    “In terms of the total MSLQ learning strategies scale, the mean response of the postgraduate students from the experimental group (4.04) was 0.8 higher than the control group (3.29).”
    Quote in the paperSubstantial claim
  • May combine two claims. 19
  • The quote only partly states this claim. 5
  • Classified as probably not a substantial claim. 18

  • May combine two claims. The quote only partly states this claim.

    Findingown data

    There was a statistically significant difference between the two groups in cognitive learning strategies (t = 7.18, p < 0.05), metacognitive self-regulation learning strategies (t = 6.07, p < 0.05), and total learning strategies (t = 6.89, p < 0.05), favoring the experimental group.

    “Furthermore, the result from the independent samples t-test, as shown in Table 4, indicates a statistically significant difference between the two groups in terms of their responses to the practices of cognitive learning strategies (t = 7.18, p < 0.05) and metacognitive self-regulation learning strategies (t = 6.07, p < 0.05) of the MSLQ learning strategies scale (t = 6.89, p < 0.05).”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    There was a statistically significant difference between the two groups in task value (t = 6.64, p < 0.05), self-efficacy for learning and performance (t = 4.33, p < 0.05), and total motivation (t = 6.25, p < 0.05), favoring the experimental group.

    “The result from the independent samples t-test, as shown in Table 3, indicates that there was a statistically significant difference between the two groups in terms of postgraduate students' responses for the task value (t = 6.64, p < 0.05) and self-efficacy for learning and performance (t = 4.33, p < 0.05) questions of the MSLQ motivation scale (t = 6.25, p < 0.05), which favored the experimental”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Through the chatbot learning environment, postgraduate students were able to better plan, manage, and monitor their learning, including setting goals, tracking cognitive learning, self-testing, and self-checking.

    “Through the chatbot learning environment, postgraduate students were able to better plan, manage, and monitor their learning, including setting goals, tracking cognitive learning, self-testing, and self-checking.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The Bashayer chatbot system enhanced postgraduate students' confidence and ability to be more self-regulated and exert more control over their learning strategies compared to peers in the traditional learning environment.

    “The results showed that the Bashayer chatbot system enhanced postgraduate students' confidence and ability to be more self-regulated and exert more control over their learning strategies when compared to their peers in the traditional learning environment.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationown data

    The results of this study are encouraging for the development of chatbot systems similar to Bashayer to support postgraduate students' successful learning.

    “The results of this study are encouraging for the development of chatbot systems similar to Bashayer to support postgraduate students' successful learning.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    Most chatbot studies focus on measuring impact on general learning motivation and cognitive skill acquisition.

    “Most chatbot studies focus on measuring impact on general learning motivation and cognitive skill acquisition.”
    Quote in the paperNot a substantial claim

  • The quote only partly states this claim.

    Study design and conductown data

    The design and content validity of the proposed Bashayer chatbot system was assessed prior to the experiment by presenting an initial version to three experts in information and communication technologies, who suggested amendments to design elements to enhance readability.

    “In order to assess the design and content validity of the proposed Bashayer chatbot system prior to the experiment, an initial version was presented to three experts who were selected for their extensive experience with information and communication technologies.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Prior studies developed chatbot systems and tested their impact on the language learning outcomes of K-12 students.

    “All the aforementioned studies developed chatbot systems and tested their impact on the language learning outcomes of K-12 students.”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Troussas et al. (2017) source

      Not checked in the free run.

    • cites Haristiani and Rifai (2021)

      Not checked in the free run.

    • cites Lin and Chang (2020)

      Not checked in the free run.

  • May combine two claims.

    Study design and conductown data

    For this study, the Arabic translation of the MSLQ had its content validity assessed by consulting three experts in educational technology proficient in English, who deemed the majority of the 38 items accurate and advised rephrasing a few for clarity.

    “For this study, the questionnaire was translated into Arabic; therefore, the validity of its content was assessed.”
    • Also stated in: § Measurement · plain
      “The experts deemed the majority of the 38 items to be accurate and advised a few items be rephrased for improved clarity.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims. The quote only partly states this claim.

    Study design and conductreasoning

    To support validity, five postgraduate students from the pilot sample navigated the system and suggested modifications to the location of main menu buttons, which were adjusted accordingly.

    “Furthermore, to support validity, five postgraduate students within the pilot sample were asked to navigate the system to provide suggestions for improvement.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The vast majority of chatbots have been employed as teaching agents and assessed using the experimental approach, and the findings largely point to improved learning performance and satisfaction.

    “The vast majority of chatbots have been employed as teaching agents and assessed using the experimental approach, and the findings largely point to improved learning performance and satisfaction (e.g., Pereira et al., 2019; Chen et al., 2020; Yin et al., 2021; Khalil and Rambech, 2022).”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Pereira et al., 2019 source

      Not checked in the free run.

    • cites Chen et al., 2020 source

      Not checked in the free run.

    • cites Yin et al., 2021 source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Chatbots have the potential to support the field of teaching-learning.

    “Chatbots have the potential to support the field of teaching–learning and act as intelligent tools that accommodate students' habits and needs (Tamayo et al., 2020; Troussas et al., 2022).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Tamayo et al., 2020 source

      Not checked in the free run.

    • cites Troussas et al., 2022 source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    From a teaching perspective, many studies have indicated that using chatbots on teaching practices yields positive results.

    “From a teaching perspective, many studies have indicated that using chatbots on teaching practices yields positive results.”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Gonda et al., 2018 source

      Not checked in the free run.

    • cites Wu et al., 2020

      Not checked in the free run.

    • cites Huang et al., 2021 source

      Not checked in the free run.

  • May combine two claims. The quote only partly states this claim.

    Study design and conductown data

    The two groups were homogeneous before the experiment began and the data followed a normal distribution, based on age distribution and Kolmogorov-Smirnov (0.20) and Shapiro-Wilk (0.15) tests with p > 0.05.

    “Therefore, the two groups were homogeneous before the experiment began and follow normal distribution of data.”
    Quote in the paperSubstantial claim

  • May combine two claims. The quote only partly states this claim.

    Study design and conductown data

    The statistical reliability of the MSLQ was measured by calculating Cronbach's alpha coefficients on a pilot sample of 10 postgraduate students, yielding values from 0.81 to 0.86 for all subscales, indicating good reliability.

    “The values of Cronbach's alpha for all subscales ranged from 0.81 to 0.86, which indicates a good level of reliability (Field, 2013).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Field, 2013

      Not checked in the free run.

  • May combine two claims.

    Interpretationreasoning

    Responding to students' questions and inquiries greatly helped in guiding them and increasing their involvement in learning activities.

    “Responding to students' questions and inquiries greatly helped in guiding them and increasing their involvement in learning activities.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductown data

    The reliability of the MSLQ was further checked by administering it twice to the same pilot sample two weeks apart, yielding a Pearson correlation of 0.84, representing high reliability.

    “The correlation value between the two applications was 0.84, which represents high reliability.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductown data

    In the current study sample, Cronbach's alpha was 0.85 for the motivation scale and 0.87 for the learning strategy scale, demonstrating a high degree of reliability for the instrument.

    “In the current study sample, the Cronbach's alpha was 0.85 for the motivation scale and 0.87 for the learning strategy scale, which demonstrated a high degree of reliability for this study's instrument.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    Most studies on chatbot technology in teaching and learning have been conducted on undergraduate and K-12 students.

    “Despite the large body of research that measured the effects of chatbot technology on teaching and learning practices, most studies have been conducted on undergraduate and K-12 students.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    Postgraduate participants using the Bashayer chatbot system and its functionalities were able to better cognitively practice learning and metacognitively regulate their learning strategies.

    “This means that postgraduate participants using the Bashayer chatbot system and its functionalities were able to better cognitively practice learning and metacognitively regulate their learning strategies.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Song et al. (2017) found that immediate interactions related to course content between learners and chatbot systems are best suited to graduate-level online courses.

    “Their findings demonstrated that immediate interactions related to course content between learners and chatbot systems are best suited to graduate-level online courses.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Song et al., 2017 source

      Not checked in the free run.

  • May combine two claims.

    Interpretationreasoning

    The Bashayer chatbot's weekly summary helped bridge students' learning gaps in subjects not yet mastered, thus building confidence in Bashayer's potential to support learning performance.

    “This helped to bridge students' learning gaps in subjects that had not yet been mastered, thus building confidence in Bashayer's potential to support learning performance.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Premisenone given

    The implementation of chatbot technology in the educational context is still in its nascent stage.

    “The implementation of chatbot technology in the educational context is still in its nascent stage, and further investigation into measuring its effectiveness in supporting learning and teaching processes is required, particularly in the context of higher education.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    In most studies, a positive trend was observed toward an increase in the use of chatbots in future education.

    “In general, in most studies, a positive trend was observed toward an increase in the use of chatbots in future education (Pereira et al., 2019; Lee et al., 2020; Chuah and Kabilan, 2021; Fidan and Gencel, 2022; Khalil and Rambech, 2022; Mendoza et al., 2022).”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Pereira et al., 2019 source

      Not checked in the free run.

    • cites Lee et al., 2020 source

      Not checked in the free run.

    • cites Chuah and Kabilan, 2021

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationown data

    This study offers motivating results that support the development of more chatbot systems that are similar to Bashayer to support successful learning.

    “This study offers motivating results that support the development of more chatbot systems that are similar to Bashayer to support successful learning.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Study design and conductnone given

    The Bashayer chatbot design was limited to the basic cognitive skills of remembering, understanding, and organizing, with control and self-regulation as the metacognitive skills.

    “The Bashayer chatbot design was limited to the basic cognitive skills of remembering, understanding, and organizing, with control and self-regulation as the metacognitive skills.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    The more meaningful the learning environment is for students, the more motivated to learn, and the more involved in learning activities, they will be.

    “The more meaningful the learning environment is for students, the more motivated to learn, and the more involved in learning activities, they will be (Fryer et al., 2019; Yin et al., 2021).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Fryer et al., 2019 source

      Not checked in the free run.

    • cites Yin et al., 2021 source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductreasoning

    The current system relied on databases that provided a specific set of responses in line with the nature of the content and tasks, which could be somewhat limiting.

    “the current system relied on databases. These were used to provide a specific set of responses in line with the nature of the content and tasks provided through the application, which could be somewhat limiting.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    The chatbot enhanced students' confidence and ability to successfully perform and accomplish learning tasks compared to a conventional learning environment.

    “In terms of self-efficacy for learning and performance, the results indicated that the chatbot enhanced students' confidence and ability to successfully perform and accomplish learning tasks compared to in a conventional learning environment.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The results may vary when the chatbot is applied to courses from other disciplines that are of an applied or practical nature.

    “Therefore, the results may vary when the chatbot is applied to courses from other disciplines that are of an applied or practical nature.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    The learning record feature gave students confidence that their learning steps were recorded and saved so that they could be followed up by the teacher anytime and anywhere.

    “This gave students the confidence that their learning steps were recorded and saved so that they could be followed up by the teacher anytime and anywhere.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Interpretationnone given

    The layout and navigation of the Bashayer chatbot system contributed to reducing distractions and cognitive load.

    “The layout and navigation of the Bashayer chatbot system contributed to reducing distractions and cognitive load.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductreasoning

    This study relied on a quantitative methodology through the application of the MSLQ scale; therefore, judgments are based on quantitative data only.

    “this study relied on a quantitative methodology through the application of the MSLQ scale; therefore, judgments are based on quantitative data only.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    These results are promising in terms of the potential of chatbot adoption to enhance learning motivation and support cognitive and metacognitive learning strategies among postgraduate students.

    “These results are promising in terms of the potential of chatbot adoption to enhance learning motivation and support cognitive and metacognitive learning strategies among postgraduate students.”
    Quote in the paperSubstantial claim
34 of 34

  • The paper relies on this without support.

    Postgraduate students are self-learners, self-motivators, and self-regulators of their learning strategies.

    “Due to the nature of postgraduate education, and the emphasis on students being self-learners, self-motivators, and self-regulators of their learning strategies, it is important to measure chatbot technology's effect on learning motivation and strategies at this level.”

  • The paper relies on this without support.

    Higher education students are autonomous, self-regulated learners.

    “This is particularly true for higher education contexts, where students are autonomous, self-regulated learners.”

  • The paper relies on this without support.

    WhatsApp is the most popular text messaging application among university students.

    “WhatsApp was chosen due to its immense popularity as a text messaging application; it is even the most popular among university students.”
3 of 3

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Current-study learning-strategies alpha differs from Table 2

    Minor

    The text gives 0.87 for the learning-strategies scale, while Table 2 gives 0.86 for that scale's current-study total.

  • Conclusion includes reasoning among assessed strategies

    Minor

    The conclusion includes reasoning in the cognitive strategies measured, but the measurement section says this study focused on remembering, understanding, and organizing instead.

  • Second research question names the wrong outcome

    Minor

    The findings section repeats the motivation question as its second research question, whereas the methodology identifies the second question as concerning learning strategies.

  • Pilot reliability range conflicts with Table 2

    Minor

    The stated pilot-sample alpha range excludes the task-value alpha of 0.78 shown in Table 2.

4 of 4

Cites

Flagged first, then by citations

3 of the 74 references couldn’t be matched to a known paper.

Research works printed but not linked: 5

  1. Almurayh, 2021, The challenges of using Arabic chatbot in Saudi universities, IAENG Int. J. Comput. Sci., 48, 190
  2. Cabrera, 2022, Peer assessment in online learning: promoting self-regulation strategies through the use of chatbots in higher education, Envisioning Report., 49, 49
  3. Calle, 2021, “Proposal for the design and implementation of Miranda: a chatbot-type recommender for supporting self-regulated learning in online environments.”, LALA'21: IV Latin American Conference on Learning Analytics, 18
  4. Lin, 2020, Enhancing post-secondary writers' writing skills with a chatbot, J. Educ. Technol. Soc, 23, 78
  5. Neuman, 1995, Single-Subject Experimental Research: Applications for Literacy

Cited by

Sorted by citations

Related

Authors
Al-Abdullatif, A. M., Al-Dokhny, A. A., & Drwish, A. M.
Affiliations
  • King Faisal University (SA)
  • Ain Shams University (EG)
  • Helwan University (EG)
Corresponding author
Al-Abdullatif, Ahlam Mohammed
ORCID
Venue
Frontiers in Psychology
Publisher
Frontiers Media SA
Published
2023-05-15
Volume
14
Pages
1129070-1129070
ISSN
1664-1078 (ISSN-L)
DOI
10.3389/fpsyg.2023.1129070
PMC
PMC10226531
OpenAlex
W4376609511
Semantic Scholar
fbca78177852d29ea4c192630e4b97b86d9adc9a
Cited by
80
References
74
Citations by year
2026: 16 · 2025: 35 · 2024: 25 · 2023: 4
FWCI
18.77
Type
journal article
Language
en
Open access
Licence
Locations
  • Frontiers in Psychology (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Greater South Information System
Funders
Deanship of Scientific Research, King Faisal University (GRANT1706)
Topics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
chatbots, WhatsApp, task-oriented chatbots, graduate students, student motivation, learning strategies, metacognitive strategies, cognitive strategies, Saudi higher education, artificial intelligence in education

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review