Learning Gain Research Articles

Blended Instructions in the New Normal and Students Learning Gains in Mathematics

The study aimed to determine the students learning gains in Mathematics as they were exposed to Blended Learning Instruction in the new normal. The study was a pretest-posttest one-group design. The data was gathered using the validated teacher-made test which was based on the Most Essential Learning Competencies (MELCs) as mandated by the Department of Education. Pretest and post-test were conducted before and after the intervention respectively. The respondents were the 41 Grade 10 students of Misamis Oriental General Comprehensive High School (MOGCHS). Mean, Standard deviation, and paired t-tests were used to analyze the data. The analysis yielded a computed P-value of 0.000 which means that a significant difference in learning gains was observed as the students were subjected to blended instruction using the module and a constant follow-up via messenger. Therefore, it is recommended that blended learning instruction in the new normal gives a positive outcome to student achievements in Mathematics.

Secondary school teacher’s conception and reflection of computer programming with Scratch

AbstractThe present study explores teachers' conception and reflection of computer programming with a Scratch in terms of technological and pedagogical aspects. A mixed research approach specifically sequential explanatory research design was used to collect quantitative and qualitative data. The population was comprised of two hundred and four in-service Mathematics, Chemistry, Physics, and Biology teachers from Kayonza district, Rwanda. However, only 34 were randomly selected to participate in the study. An achievement test and structured interview were used to collect quantitative and qualitative data, respectively. The quantitative data obtained from pre- and post-tests were analyzed using a pairedttest, and the data from the interview was analyzed by descriptive, and interpretive analyses. It was revealed that secondary school teachers have a respectable conception and constructive reflection of Scratch programming once attending scratch training. Quantitative findings showed that there was an important difference in the mean among pre- and post-tests with 0.171 learning gain and an effect size of 0.53 (df = 33,p < 0.05). It was also revealed that Scratch is an operational instructional tool for teaching and learning Mathematics and Sciences. Furthermore, teachers articulated progressive views of using scratch in teaching and learning Mathematics and Sciences as it supports them to visualize abstract content, improves students' interest and impetus, critical thinking, and problem-solving skills, and acts as an assessment tool.

Facilitating Mathematical Competencies Development for Undergraduate Students During the Pandemic Through ad-hoc Technological Learning Environments

In this article we show how to facilitate the development of mathematical skills using 3D surface visualization tools and virtual environments in an online, project-based learning context. The “Lumen” software is presented, which is an ad-hoc solution, designed and developed to visualize and combine mathematical surfaces in 3D, based on their associated equations. Several activities were designed with the use of Lumen, to measure the learning gain and problem-solving skills of the students, obtaining that a mean learning gain of 43% was observed on 242 students on the analysis of the pre- and post-tests for the first monitored activity, while a mean learning gain of 30% was observed on 210 students on the analysis of the second monitored activity. Based on these analyses, we make the point that although remote learning in the context of the COVID-19 pandemic poses difficult challenges for learners and professors, the use of ad-hoc technological applications is an important resource that supports the reinterpretation of the learning process, as it shifts the focus to the development of skills through active learning.

Data-driven adaptive tuning of iterative learning control

In this paper, we propose two data-driven adaptive tuning (DDAT) approaches of iterative learning control (ILC) for nonlinear non-affine systems. First, a compact-form iterative dynamic linearization (CFIDL) method is introduced to transfer the original nonlinear system into a linear data model. Then, we design an objective function for the tuning of the learning gains of a PD-type ILC law. By optimizing the designed cost function subjected to the linear data model, a CFIDL-based DDAT method is proposed, where only the real I/O data are used without requiring any mechanistic model information. Furthermore, the results are extended by introducing a partial-form iterative dynamic linearization (PFIDL) method for the purpose of utilizing more additional control information. Following the similar steps, a PFIDL-based DDAT method is developed for learning gain tuning of the PD-type ILC scheme. Both the proposed DDAT methods can help the PD-type ILC have a better robustness against to the uncertainties since they can use the real I/O data to iteratively tune the learning gains. The convergence of the DDAT-based PD-type ILC methods has been proved rigorously. The effectiveness of the two proposed DDAT-based ILC methods are further verified through simulations.

Learning Control for Networked Stochastic Systems With Random Fading Communication

The learning control strategy is studied for networked stochastic systems, where the output and input data are transmitted through multiple independent fading channels. The traditional P-type learning control scheme is revised according to the specific fading positions, where the constant learning gain is replaced by a variable one to suppress the effect of various uncertainties. Strong convergence of the proposed scheme is established under random fading phenomena and system noise. The input error is shown convergent to zero as the cycle number increases. Two numerical examples demonstrate the applications of the proposed scheme.

Preferences of the 1st year medical students on various teaching methods and their feedback on curriculum quality in Biochemistry

Objectives: Medical teaching requires introduction of new teaching methods to cover the vast curriculum in stipulated time. Apart from conventional teaching, newer teaching learning methods such as video clippings, problem-based learning (PBL), seminars, early exposure to patients, hospital laboratory visits, debates, quiz, and group discussions need to be introduced. The study was conducted to gauge the student’s perception regarding the teaching methodology adopted by the department of Biochemistry for the 1st year MBBS students. Along with this, feedback was also taken to assess the student’s views on their present assessment system as well as on various aspects of the current MBBS curriculum and on their relationship with their teachers. Materials and Methods: This was an observational study conducted in the department of Biochemistry and the data were collected using a pre-designed questionnaire from the 1st year MBBS students after completion of the 1st year Biochemistry course. Results: The questionnaire evaluated different teaching methods for various topics in Biochemistry. Among 243 students included in the study, didactic lecture was preferred by 80 students for endocrinology and 82 for cancer biology topics. Debate was preferred for the topic of nutrition (n = 82). Ninety-one students chose case-based learning for learning clinical Biochemistry. Video-based learning was preferred for the topic of molecular biology by 80 students. Conclusion: Students prefer different combinations of teaching learning method for better understanding of the subject. Early clinical exposure and effective tutorial sessions will definitely improve the learning gain among pre-clinical students.

Investigating the Impact of the COVID-19 Pandemic on Undergraduate Business Education: Using Learning Gain as a Measure to Compare Two Cohorts of Marketing Students

This paper considers management education and specifically how student learning has been impacted by the online replacement teaching offered by universities during the COVID-19 pandemic. The study utilizes a learning gain model which considers the students’ own perception of their learning, and separates the provision of theoretical explicit knowledge (distance travelled) from that of practical tacit understanding (journey travelled). In 2019, data were collected from a cohort of marketing students studying for an undergraduate UK business studies degree. In 2021, data were again collected from a new cohort of students studying the same business studies degree course, but this time during the COVID-19 period. A comparison was undertaken to identify any differences in learning gain. Overall, a drop in perceived learning was reported, although in a few areas, an indication of stronger learning was identified. Interestingly, female students reported the most significant drop in their learning related to journey travelled, whereas for male students, it related to distance travelled.

Real-Time Implementation of Iterative Learning Control for an Electro-Hydraulic Servo System

Electro-hydraulic servo systems (EHSSs) are nonlinear and uncertain due to their inappropriate fluid levels, air temperature, friction, and leakage. The finite-time tracking control is difficult with the use of a proportional, integral, and derivative (PID) controller, which no longer provides adequate and achievable control performance over the whole operating range. This has led to the idea of an iterative learning controller (ILC). An intelligent and memory-based learning control approach that attempts to imitate the human way of thinking. The proposed ILC has an additional learning gain, learning filter, and robustness filter to enhance the finite-time tracking performance and stability improvement. This study is focused on the design of the ILC to regulate the servo spool valve of an EHSS, which in turn controls the displacement of a hydraulic cylinder. In simulation and experimentation, vital parameters such as overshoot and settling time in the varieties of tests, the ILC has shown better results when compared to conventional PID controllers. In step input tracking at different operating points over 0-250 mm, the ILC has 40% less overshoot and settles 12-15 s faster than the PID controller. In sinewave tracking and disturbance rejection, the PID controller performs better than the ILC in integral square error and integral absolute error as the error indices are not considered as the objective function in the design of the controller. During a robustness test, the ILC rejects the uncertainty, which evidences the effectiveness of the proposed controller.

Supporting reflection to improve learning from self-generated concept maps

Creating concept maps is considered to be a powerful means for learning. It requires students to systematically organize and integrate their knowledge, which can foster meaningful learning. However, students scarcely spontaneously engage in the (meta)cognitive processes necessary for effective knowledge integration, such as reflection, which can hamper the effectiveness of concept mapping for learning. This study explores the effect of additional support that stimulates reflection by means of expert examples, reflection prompts, and classroom discussion. First-year technical vocational students (N = 144, Mage = 17.5 years) studied electricity-related topics in an online learning environment and created concept maps about their knowledge. Students’ concept maps were supplemented with either (1) no support (control condition), (2) an expert example (a combined concept map, containing their own and an expert example concept map, with differences highlighted), (3) an expert example and reflection prompts students had to process individually, (4) an expert example and reflection prompts students had to process individually after a teacher-guided classroom discussion. Students in the classroom discussion condition showed higher learning gains compared to all other conditions. This can be explained by the quality of their reflection, which proved to be a significant predictor of learning gain.

Quantification of Learning Gains in a Science CURE: Leveraging Learning Objectives to Substantiate and Validate the Benefits of Experiential Education

Course‐based Undergraduate Research Experiences (CURE) aim to provide college students with hands‐on experiences to develop research skills and complex thinking. Development of these abilities is invaluable as students undertake further education and begin critical professions. Regardless of eventual career aspirations, CUREs make it possible for every student to experience the enchantment of science in its authentic form. Performing research serves to galvanize inquiring minds that serve as role models for future generations of scientists. Science, Technology, Engineering and Math (STEM) disciplines as a whole suffer from high rates of student attrition. Notably, students from underrepresented groups enter STEM disciplines at similar rates and with similar interest levels as White students, but do not persist at the same rates. CUREs have proven to be an indispensable model to expose every student, regardless of race, socioeconomic status or family obligations, to the process of science first hand. While many CURE curricula are freely available online, faculty are hesitant to adopt this new style of teaching. Using established anticipated learning outcomes (ALO) designed specifically for the Biochemistry Authentic Student Inquiry Laboratory (BASIL) CURE, this study aims to gauge student learning objective mastery quantitatively. Likert scale‐based analysis is employed to evaluate the level of content mastery student responses demonstrate. Assignment questions were designed to correspond to the most critical learning objectives, as identified by BASIL faculty. Researchers spent significant effort designing and refining laboratory assignment questions that correspond to and can reliability and consistently to gage mastery of the ALOs.Data of student mastery spanning 4 semesters will be discussed. Students showed significant learning gains in all four semesters/modalities. Greater mastery of bioinformatic ALOs during remote learning shows quality education can be enhanced and improved by technology. The student’s mastery of wet‐lab ALOs coincided with our findings that lab courses need enhanced strategies to teach critical STEM lab‐research skills in an online setting. Novel assessment and instruction strategies targeted to learning mastery gaps identified as part of this work will pave the way for wider CURE adoption. Ultimately, serving as a platform to expose every undergraduate student to vital STEM research experiences.

External Collaboration Results in Student Learning Gains and Positive STEM Attitudes in CUREs

The implementation of Course‐Based Undergraduate Research Experiences (CUREs) has made it possible to expose large undergraduate populations to research experiences. For these research experiences to be authentic, they should reflect the increasing collaborative nature of research. While some CUREs have expanded with multiple schools across the nation, it is still unclear how a structured extramural collaboration between students and faculty from an outside institution affects student outcomes. In this study, we established three cohorts of students: 1) no‐CURE 2) single institution CURE (CURE) and 3) external collaborative CURE (ec‐CURE) and assessed academic and attitudinal outcomes. The ec‐CURE differs from a regular CURE in that students work with faculty member from an external institution to refine their hypothesis and discuss their data. The sharing of ideas, data and materials with an external faculty allowed students to experience a level of collaboration not typically found in an undergraduate setting. Students in the ec‐CURE had the greatest gains in experimental design, self‐reported course benefits, scientific skills and STEM importance. Importantly this study occurred in a diverse community of STEM disciplinary faculty from 2‐ and 4‐year institutions illustrating that exposing students to structured external collaboration is both feasible and beneficial to student learning.

PERFORMANCE ANALYSIS OF WAQF INSTITUTION USING BALANCED SCORECARD ANALYSIS: CASE STUDY AT LAZNAS YATIM MANDIRI

This research aims to measure the performance of the waqf institution (LAZNAS Yatim Mandiri) using a balanced scorecard (BSC). This study uses quantitative and qualitative analysis or mixed-method by using a balanced scorecard (BSC). The Balanced Scorecard is used to measure performance from both a financial perspective and a non-financial perspective, which includes four main perspectives: (1) finance, (2) customers, (3) internal business processes, and (4) learning and growth. The study found that an overall BSC score of 85,6% shows that the performance of LAZNAS Yatim Mandiri is categorized as very good. From each perspective, customer perspective is the highest BSC score, followed by financial perspective and internal business while learning and growth perspective gain the lowest score. The BSC suggests a direction of priority to improve each strategic goal of perspective. Customer satisfaction becomes the first place, followed by waqf collection and distribution as the second priority. The next priority is employee satisfaction while keeping other strategic goals to be maintained. The findings of this study could help Islamic philanthropic institutions define their vision and strategy, as well as change their vision and strategy into specific activities, by implementing measures that are accurate and comprehensive, as well as providing information that is accurate and correct for managers to make business decisions.

Perceived Level of Usability as an Evaluation Metric in Adaptive E-learning: A Case Study with Dyslexic Children.

The global spread of COVID-19 has shifted the learning process towards e-learning. In this context, a critical challenge for researchers is to understand and evaluate the effectiveness of e-learning, especially when the learning is adapted to the needs of individual users. In this work we argue that the learner’s perception of the level of usability of a system is a valuable metric that gives an insight into the learners’ engagement and motivation to learn. Little attention has been paid to this metric. In this paper we explore why this is important and valuable. We present a case study which uses the System Usability Scale (SUS) questionnaire to measure the user’s perception of usability as an indirect (proxy) measure of engagement. A between-subject experiment was conducted with 41 learners with dyslexia. The intervention group used the adaptive version of the e-learning system that matched the material to the needs of the learner. The control group used a standard version. At the end, learning gain and SUS scores were assessed. The correlation between learning performance and the perceived level of usability was positive and moderate (0.517, p < 0.05) among participants in the intervention group. However, learning performance and perceived level of usability were unrelated in the control group (− 0.364, p > 0.05). From this, and other work, it appears that using a learner’s assessment of the usability of a system is an effective way to measure their attitude to their learning. It reflects their perception of its suitability to their needs and this, in turn, is likely to affect their engagement and motivation. As such, this provides an effective instrument to judge whether adaptation based on learner needs has been successful.

Performance Evaluation of SeisTutor Using Cognitive Intelligence-Based "Kirkpatrick Model".

The classroom learning environment facilitates human tutors to interact with every learner and get the opportunity to understand the learner's psychology and then provide learning material (access learner prior knowledge and well align the learning material as per learner requirement) to them accordingly. Implementing this cognitive intelligence in intelligent tutoring system is quite tricky. This research has focused on mimicking human tutor cognitive intelligence in the computer-aided system of offering an exclusive curriculum to the learners. The prime focus of this research article is to evaluate the proposed SeisTutor using Kirkpatrick's four-phase evaluation model. Experimental results depicting the enhanced learning gain through intelligence incorporated SeisTutor as against the intelligence absence are demonstrated.

THE EFFECT OF USING BALL TOSS STRATEGY IN TEACHING VOCABULARY AT THE FOURTH GRADE OF SDN 023 PANDAU JAYA

The purpose of this research was to find out there was significant effect of the students who were taught by using ball toss strategy better than the students who were not taught on vocabulary mastery at the fourth grade of SDN 023 Pandau Jaya. This research was Quasi Experimental research. The population of this research was the the fourth grade of SDN 023 Pandau Jaya. The number of sample was 56 students; Experimental class was IV.A consisting of 28 students, and Control class was IV.C consisting of 28 students. After calculating U-Mann whitney test, the researcher found that Asymp.Sig 2 tailed &lt; Significant level (0.00 &lt; 0.05), so that Alternative Hypothesis was accepted, it meant that there was significant effect of using Ball Toss Strategy toward students’ vocabulary mastery at the fourth grade of SDN 023 Pandau Jaya and the average post-test score of experimental class was 71.42, increased from pre-test score 54.10. The average post-test on control class was 63.57 was lower than Experimental class. N-Gain of this research was 0.35, it was categorized middle. As the conclusion, there was different vocabulary mastery of the students who received in class instruction of ball toss strategy than students who did not receive instruction of ball toss strategy. REFERENCES Aefsky, Fern. 2000. Making decision about diverse learners. United States. Handbooks, manuals. Allen, Janet. 1999. Word and Word in teaching Vocabulary in Grade 4-12. Portland: Stelhouse Publishers. Alicia. 2010. Teaching Vocabulary by Using Ball Toss Review Strategy at Elementary School 144 Padang. Retrieved on April 2014. http://ejournal-s1.stkip-pgri-sumbar.ac.id/index.php/Inggris/article/view/737/728 Asfiyah. 2011. The Use of Ball Toss Strategy to Improve Students Vocabulary in Concrete Noun (An Experimental Research at the Second Grade of MTS. Mafatihut Thullab An-Nawawy Surodadi Jepara in Academic Year of 2010/2011. Retrieved on April 2014. Unpublished Thesis: http://library. walisongo.ac.id/digilib/files/disk1/115/jtptiain-gdl-asfiyah-5707-1-053411341.pdf Creswell, Jhon W, 2005. Educational Research Planning, Conducting, and Evaluating Quantitative and Qualitative Research. Second Edition. USA: University of Nebraska-Linclon. Eckersley, C.E. 1960. A Comprehensive English Grammar for Foreign Language Students. London: Longman. Hasanah. 2013. Teaching English Vocabulary Using Ball Toss Strategy at the Fourth Grade Students of SDN Cibeber Mandiri 1 Cimahi in Academic Year 2012-2013.Retrieved on April 2014. Unpublished thesis: http://publikasi.stkipsiliwangi.ac.id/wp-content/blogs.dir/2 /files/ 2013/11 /0922055567-Hasanah. Hornby, AS.2000. Oxford Advanced Learner’s Dictionary. Oxford university Press. Khaty. 2010. 40 active strategy learningstrategies inclusive Classroom. United States. Lybrary of congres catalog. Leaver,et al.2005. Achieving Success in Second Language Acquisition. Cambridge University Press. Linse, Caroline. 2006. Practical English Language Teaching: Young Learners. NewYork: McGraw Hill. Meltzer,D.E. 2002. The relationship between Mathematics Preparation and Conceptual Learning Gains in Physic: A possible: “hidden variable” in diagnostic pretest score. American Journal. Nunan, David. 1991. Practical English Language. America: Cambridge University Press. Septiani. 2013. Teaching Vocabulary Using Ball Toss Strategy on Students of Elementary (A Case Study at the Sixth Grade SD Pandu Bandung. Retrieved on April 2014. Unpublished thesis: http://publikasi.stkipsiliwangi.ac.id/wp-content/blogs.dir/2/files/2013/11/09220536-Septiani. Sugiyono, Prof.Dr. 2010. Statiska Untuk Penelitian. Bandung. CV.Alfabeta Toby. 2002. Strategies for teaching. San Francisco: Market Strevrt. Ur, Penny. 1991. A Course in Language Teaching: Practiceand Theory. Cambridge University Press. Zulkarnain. 2010. Statiska Penelitian. Pekanbaru: Cendekia Insani Pekanbaru.

Evaluating the Effect of Rich Vocabulary Instruction and Retrieval Practice on the Classroom Vocabulary Skills of Children With (Developmental) Language Disorder.

Learning new vocabulary has been identified as a challenge for students with (developmental) language disorder ((D)LD). In this study, we evaluate the effects of two active learning methods, (a) retrieval practice (RP) and (b) rich vocabulary instruction (RVI), in a group of students with (D)LD in secondary school. A quasi-experimental counterbalanced within-subject design was used to compare and evaluate the effect of RP and RVI on learning Tier 2 vocabulary, with target and control words as dependent measures. Eleven students with (D)LD (M age = 14.9 years) attending a language unit participated. RP and RVI were implemented in regular classroom activities during 16 lessons (eight lessons/instructional condition). Learning was assessed by comparing performance on a pretest session 1-2 weeks prior, with posttest performance 1 week after each instructional condition. The learning gain for RP was superior to that for RVI, both with respect to the Bayesian probabilistic estimations for target words relative to control words and in direct comparison with RVI. Only weak evidence was found for RVI with respect to the Bayesian probabilistic estimations for target words relative to control words. All participants showed positive learning gains following RP, whereas the outcome for RVI was more diverse. This initial work suggests that RP promotes larger learning gains relative to RVI and promotes learning across language profiles. This study extends previous studies by exploring the implementation of RP in regular classroom activities and by using more complex to-be-learned material (Tier 2 words).

An Augmented Reality Based Mobile Photography Application to Improve Learning Gain, Decrease Cognitive Load, and Achieve Better Emotional State

Taking photos by mobile phones has become an indispensable part of people's daily life with the popularity of smartphones. However professional photography content is also needed for taking high-quality photos by mobile phones as ones taken by professional cameras. Existing learning tools for photography can't provide photographic practice while presenting theoretical content, nor give real-time photography guidance according to the environment. Mobile augmented reality (AR) technology provides a new way to solve these problems by creating a real learning situation. Therefore, an innovative AR-based mobile photography application (ARMPA) is designed and developed as a method to connect theory and practice. Based on Learning-by-Doing instructional strategy, the ARMPA can timely and synchronously display the theoretical content of photography in the form of text and images corresponding to learners' practical operation. Moreover, it can provide learners real-time interaction and guidance by using AR environment sensing technology. The effect of ARMPA on learning gain and cognitive load is assessed by traditional methods of pre/post-test and questionnaires. To objectively explore the effectiveness of ARMPA from a cognitive and emotional perspective, we measure and extract four emotional state indexes of electroencephalogram (EEG) including engagement (ENG), relaxation (MED), interest (INT) and focus (FOC). Compared to traditional two-dimension (2 D) application (APP), ARMPA improves learners’ learning gains, decreases learners’ cognitive loads. The participants in the AR group achieve better emotional states than those in the 2 D group. This study provides some empirical evidence for AR technology to boost mobile phone photography.

The Efficacy of Completing Form-focused Tasks Collaboratively vs Individually: Utilizing Interventionist Dynamic Assessment to Quantify Learning Gains

Many language teachers employ collaborative learning within their classrooms. However, expectations surrounding the efficacy of working collaboratively need to be empirically verified. This study employed dynamic assessment to investigate whether learners who are situated within an undergraduate Qatari EFL context learn second language grammatical structures more effectively by working either collaboratively with their peers or individually. Interventionist dynamic assessment was used to quantify the extent of the learning gains made by male Arabic undergraduate EFL learners (N = 52) three times (pretest, posttest, and delayed posttest) over a 12-week period. In between the pretest and the posttest, six form-focused treatment tasks were administered. The experimental group (n = 20) completed the tasks collaboratively with their peers; a comparison group (n = 16) completed the tasks individually; and a control group (n = 16) did not complete the tasks. The target structures were the simple past passive and the present continuous passive. A Mood’s median test (Mood, 1954) found no statistically significant differences between the collaborative condition and the individual condition. Although measuring emergent abilities which are still in the process of developing provided a more complete picture of the efficacy of working collaboratively, the lack of a statistically significant difference between the performances of the experimental and comparison groups for both target structures suggests that working collaboratively is not statistically more effective in facilitating learners’ linguistic development than working individually.

A Quasi-Experimental Evaluation of Teaching Software Testing in Software Quality Assurance Subject during a Post-Graduate Computer Science Course

Software testing is regarded as a key activity in the software development cycle, as it helps information technology professionals to design good quality software. Thus, this is an essential activity for the software industry, although with all its nuances high priority is still not being given to learning about it at an academic level. The purpose of this work is to investigate a teaching strategy for software testing which involves acquiring academic skills within a curriculum based on active teaching methodologies. A teaching model was designed for this to coordinate the different areas of a subject, and then a controlled quasi-experiment was carried out in a post-graduate course to evaluate the application of this model. The results obtained demonstrate that there was a considerable learning gain in the experimental group that adopted the teaching approach when compared with the control group that relied on a traditional approach. The student t-test was employed to determine the learning efficiency.

Course complexity in engineering education using E-learner's affective-state prediction

PurposeAffective states in learning have gained immense attention in education. The precise affective-states prediction can increase the learning gain by adapting targeted interventions that can adjust the changes in individual affective states of students. Several techniques are devised for predicting the affective states considering audio, video and biosensors. Still, the system that relies on analyzing audio and video cannot certify anonymity and is subjected to privacy problems.Design/methodology/approachA new strategy, termed rider squirrel search algorithm-based deep long short-term memory (RiderSSA-based deep LSTM) is devised for affective-state prediction. The deep LSTM training is done by the proposed RiderSSA. Here, RiderSSA-based deep LSTM effectively predicts the affective states like confusion, engagement, frustration, anger, happiness, disgust, boredom, surprise and so on. In addition, the learning styles are predicted based on the extracted features using rider neural network (RideNN), for which the Felder–Silverman learning-style model (FSLSM) is considered. Here, the RideNN classifies the learners. Finally, the course ID, student ID, affective state, learning style, exam score and course completion are taken as output data to determine the correlative study.FindingsThe proposed RiderSSA-based deep LSTM provided enhanced efficiency with elevated accuracy of 0.962 and the highest correlation of 0.406.Originality/valueThe proposed method based on affective prediction obtained maximal accuracy and the highest correlation. Thus, the method can be applied to the course recommendation system based on affect prediction.