Computer-assisted Language Learning Research Articles

Heutagogical-based ICALL environment

The use of Intelligent Computer Assisted Language Learning (ICALL) in foreign language learning holds great promises, but the identification of rigorous design principles to develop students’ capability through practical learning design are still insufficient. As capability concerns how people use their competencies in the unknown rather than in familiar situations, ensuring students' capability development becomes crucial in today’s complex, dynamic, and rapidly changing system of modern society. One critical question to firstly answer regarding the numerous variety and available options of ICALL applications is what and how to choose appropriate and relevant ICALL applications which would effectively enhance students’ capability. This paper proposes a framework for the intervention design of the ICALL learning environment to develop EFL students’ capability based on the pedagogy-andragogy-heutagogy continuum and the authentic learning framework.

The Mechanism of Niaoduqing Granules in Treating Diabetic Nephropathy Based on Network Pharmacology and Molecular Docking

Objective: It's to explore the mechanism of action of Niuduqing Granules in the treatment of diabetic nephropathy using network pharmacology methods and molecular docking. Methods: The active ingredients and targets of Uremiaqing granules were screened through the TCMSP database; targets related to diabetic nephropathy were screened in GeneCards and OMIM databases; Venn diagrams were drawn using Venny2.1 software to obtain common targets for drug treatment of diseases; Cytoscape software was used to construct "Uratoxicosis" "Qing granule-ingredient-target-DN" interaction network; build a PPI network on the STRING website to screen core targets for drug treatment of diseases; conduct GO and KEGG functional analysis of common targets through R language software; use AutoDock and PyMOL software to analyze Molecular docking of active pharmaceutical ingredients with core targets. Results: 138 potential active ingredients and 169 therapeutic targets of Niduqing Granules were screened out. The targets mainly involve the regulation of biological processes involve antioxidant stress, external response, etc., and are mainly enriched in lipids, atherosclerosis, and PI3K/AKT. and other signal pathways. Molecular docking shows that the core active ingredient and core target have good binding activity. Conclusion: The study reveal that Niaduqing Granules have the characteristics of multi-component, multi-target, and multi-pathway regulation. The mechanism of action of Niaduqing Granules in treating diabetic nephropathy may be related to anti-oxidative stress, regulation of cellular immunity, etc.

How To Motivate Language Learning Environment: CALL Before And After The Pandemic Of Covid-19

Integrating information technology into teaching and learning foreign languages holds significant importance for the education system of our country. This serves as a crucial foundation for shaping the core generation of the future, aiding the nation's development, and advancing on the path of international integration. However, the application of information technology in foreign language education is currently prevalent primarily in schools located within major cities. To achieve the good effectiveness of Computer Assisted Language Learning (CALL), suitable solutions tailored to specific localities are necessary, which is the motivation for this study. I conducted this study focusing on high school students in Nha Trang to understand their attitudes towards the use of information technology in learning English before and after the pandemic Covid 19. This understanding was then used to discuss and propose several appropriate solutions aimed at cultivating a self-directed, creative, and engaging learning environment. This research has the potential to contribute towards generating general solutions for the implementation of information technology in teaching and learning across Vietnam.

Insights into the epidemiology and clinical aspects of post-COVID-19 conditions in adult

Objectives While most individuals infected with COVID-19 recover completely within a few weeks, some continue to experience lingering symptoms. This study was conducted to identify and describe the clinical and subclinical manifestations of adult patients from the long-term effects of COVID-19. Methods The study analyzed 205 medical records of inpatients (age ≥ 16 years, ≥ 4 weeks post-COVID-19 recovery, and a negative SARS-CoV-2 status at enrollment) at Thong Nhat Hospital, Vietnam, from 6 September 2021 to 26 August 2022, using R language software. Results The majority of patients hospitalized with long COVID-19 symptoms (92.68%) had normal consciousness. The most common symptoms on admission were fatigue (59.02%), dyspnea (52.68%), and cough (42.93%). In total, 80% of patients observed respiratory symptoms, primarily dyspnea, while 42.44% reported neurological symptoms, with sleep disturbance being the most common. Noticeably, 42.93% of patients experienced respiratory failure in the post-COVID-19 period, resembling acute respiratory distress syndrome. Discussion These findings provide crucial insights into the epidemiology, clinical, and subclinical aspects of post-COVID-19 conditions, shedding light on the prevalence of common symptoms and the demographic distribution of affected patients. Understanding these manifestations is vital for patient well-being, improved clinical practice, and targeted healthcare planning, potentially leading to better patient care, management, and future interventions.

Influencing and moderating variables in informal digital learning of English through a structural equation model

With the rapid development of information technologies, informal digital learning of English has emerged as an innovative computer-assisted language learning method. This study aims to examine the variables influencing informal digital English learning through a structural equation model since no studies have been devoted to this topic. Through data collected from a comprehensive questionnaire (n = 1047) and the structural equation model through AMOS 24.0, this study concludes: (1) The informal digital English learning activities, learners’ grit, self-confidence, feedback handling skills, and interest enhancement positively and significantly predict willingness to communicate in informal digital English learning contexts significant at p = 0.05; (2) Willingness to communicate negatively and significantly predicts vocabulary knowledge scores in informal digital English learning contexts at p = 0.05; (3) Gender, age, and major significantly moderate the relationships between constructs in informal digital English learning contexts at p = 0.05, which is considered to have filled a research gap in informal digital English learning contexts. Future research directions are suggested.

HealthFaaS: AI-Based Smart Healthcare System for Heart Patients Using Serverless Computing

Heart disease is one of the leading causes of death worldwide, and with early detection, mortality rates can be reduced. Well-known studies have shown that the latest Artificial Intelligence (AI) can be used to determine the risk of heart disease. However, existing studies did not consider dynamic scalability to get the best performance from these AI models in case of an increasing number of users. To solve this problem, we proposed an AI-powered smart healthcare framework called HealthFaaS, using the Internet of Things (IoT) and a Serverless Computing environment to reduce heart disease-related deaths and prevent financial losses by reducing misdiagnoses. HealthFaaS framework collects health data from users via IoT devices and sends it to AI models deployed on a Google Cloud Platform (GCP) based serverless computing environment due to its advantages such as dynamic scalability, less operational complexity, and a pay-as-you-go pricing model. The performance of five different AI models for heart disease risk detection is evaluated and compared based on key parameters such as accuracy, precision, recall, F-Score, and AUC. Experimental results demonstrate that the LightGBM model gives the highest success in detecting heart diseases with an accuracy rate of 91.80%. Further, we have tested the performance of the HealthFaaS framework in terms of Quality of Service (QoS) parameters such as throughput and latency against the increasing number of users and compared it with a non-serverless platform. In addition, we have also evaluated the cold start latency using a serverless platform which determined that the amount of memory and the software language makes a direct impact on the cold start latency.

An open-source natural language processing toolkit to support software development: addressing automatic bug detection, code summarisation and code search.

This paper aims to introduce the innovative work carried out in the Horizon 2020 DECODER project - acronym for "DEveloper COmpanion for Documented and annotatEd code Reference" - (Grant Agreement no. 824231) by linking the fields of natural language processing (NLP) and software engineering. The project as a whole addresses the development of a framework, namely the Persistent Knowledge Monitor (PKM), that acts as a central infrastructure to store, access, and trace all the data, information and knowledge related to a given software or ecosystem. This meta-model defines the knowledge base that can be queried and analysed by all the tools integrated and developed in DECODER. Besides, the DECODER project offers a friendly user interface where each of the predefined three roles (i.e., developers, maintainers and reviewers) can access and query the PKM with their personal accounts. The paper focuses on the NLP tools developed and integrated in the PKM, namely the deep learning models developed to perform variable misuse, code summarisation and semantic parsing. These were developed under a common work package - "Activities for the developer" - intended to precisely target developers, who can perform tasks such as detection of bugs, automatic generation of documentation for source code and generation of code snippets from natural languages instructions, among the multiple functionalities that DECODER offers. These tools assist and help the developers in the daily work, by increasing their productivity and avoiding loss of time in tedious tasks such as manual bug detection. Training and validation were conducted for four use cases in Java, C and C++ programming languages in order to evaluate the performance, suitability, usability, etc. of the developed tools.

Molecular markers of type II alveolar epithelial cells in acute lung injury by bioinformatics analysis

In this study, we aimed to identify molecular markers associated with type II alveolar epithelial cell injury in acute lung injury (ALI) models using bioinformatics methods. The objective was to provide new insights for the diagnosis and treatment of ALI/ARDS. We downloaded RNA SEQ datasets (GSE109913, GSE179418, and GSE119123) from the Gene Expression Omnibus (GEO) and used R language package to screen differentially expressed genes (DEGs). DEGs were annotated using Gene Ontology (GO), and their pathways were analyzed using Kyoto Encyclopedia of Genes and Genomes (KEGG). DEGs were imported into the STRING database and analyzed using Cytoscape software to determine the protein network of DEGs and calculate the top 10 nodes for the hub genes. Finally, potential therapeutic drugs for the hub genes were predicted using the DGIdb database. We identified 78 DEGs, including 70 up-regulated genes and 8 down-regulated genes. GO analysis revealed that the DEGs were mainly involved in biological processes such as granulocyte migration, response to bacterial-derived molecules, and cytokine-mediated signaling pathways. Additionally, they had cytokine activity, chemokine activity, and receptor ligand activity, and functioned in related receptor binding, CXCR chemokine receptor binding, G protein-coupled receptor binding, and other molecular functions. KEGG analysis indicated that the DEGs were mainly involved in TNF signaling pathway, IL-17 signaling pathway, NF-κB signal pathway, chemokine signal pathway, cytokine-cytokine receptor interaction signal pathway, and others. We identified eight hub genes, including IRF7, IFIT1, IFIT3, PSMB8, PSMB9, BST2, OASL2, and ZBP1, which were all up-regulated genes. We identified several hub genes of type II alveolar epithelial cells in ALI mouse models using bioinformatics analysis. These results provide new targets for understanding and treating of ALI.

Enhancing EFL Learners Diphthong Pronunciation Ability’s using PRAAT

<div class="WordSection1"><p>Pronunciation is one of the most important aspects for learners in studying English. Today, pronunciation tends to be neglected by instructors in EFL (English as a Foreign Language) classes, especially for vowel sounds. Computer-assisted language learning (CALL) is one of the alternative methods in enhancing students’ ability in pronunciation. PRAAT is software used to measure the quality of students’ pronunciation. They were able to enhance their pronunciation practice by using the visual spectrogram. The purpose of this research was to determine the efficacy of employing CALL in pronunciation classes. The numbers of students in this research were 30 Acehnese EFL students. The methodology was quantitative through experimental research. A Word list was used as an instrument to obtain data from the learners. Based on the results, there was a significant improvement after the learning process. The learners had difficulty with five significant mistake sounds: [e], [ei], [i], [e], [e]. They recognized these sounds as monophthongs. This inaccuracy was caused by unfamiliarity with English diphthongs, because these sounds did not found in L1 and L2. After a few repetitions, the students began to use more diphthongal and higher F1 and F2 sounds. Hence, it can be concluded that the CALL had a positive impact in enhancing the student’s ability in pronunciation.</p></div>

Examining the impacts of learner backgrounds, proficiency level, and the use of digital devices on informal digital learning of English: an explanatory mixed-method study

In Computer-assisted language learning (CALL), the relationship between learner background and classroom-based digital language learning has been widely studied; however, little attention has been directed to informal digital learning of English (IDLE), a crucial subdomain of inquiry of CALL. Building on our prior IDLE study, this explanatory mixed-method study set out to examine and explore the relationships between IDLE and learners’ demographics by drawing on questionnaire responses collected from 1080 Chinese university EFL learners and interview results from nine selected survey respondents. Quantitative results revealed the variance in IDLE that can be accounted for individually and in concert with learners’ demographic information, socioeconomic backgrounds, proficiency levels, and their use of digital devices and the predicting power of these factors. The results indicated that gender, university type, students’ self-rated speaking skills, standardized test results, and the number of digital devices in use contributed to the variance of IDLE. Learners’ majors, writing skills, devices using time, ethnicity, family income, and regional backgrounds predicted their engagement in IDLE activities. Qualitative results further explained these findings by highlighting how learners of various backgrounds engaged in IDLE practices in specific settings. Cross-case content analysis of the interview results provided interpretations and an in-depth understanding of learners’ situated IDLE experiences. Future studies are suggested to focus more on ethnic minority groups, students from less developed regions and ordinary universities, and non-English majors, who are less likely to benefit from IDLE activities. More attention should also be paid to how students of various sociocultural backgrounds actually engage with IDLE activities in various settings across time to address IDLE dynamics.

Bibliometric analysis of electrochemical disinfection: current status and development trend from 2002 to 2022.

The removal of waterborne pathogens from water is critical in preventing the spread of waterborne diseases. Electrochemical methods have been extensively researched and implemented for disinfection, primarily owing to their simplicity, efficiency, and eco-friendliness. Thus, it is essential to conduct a review about the research progress and hotspots on this promising technique. In this paper, we provided a comprehensive bibliometric analysis to systematically study and analyze the current status, hotspots, and trends in electrochemical disinfection research from 2002 to 2022. This study analyzed literature related to electrochemical disinfection or electrochemical sterilization published in the Web of Science database from 2002 to 2022 using CiteSpace and Biblioshiny R language software packages. The analysis focused on the visualization and assessment of annual publication volume, discipline and journal distribution, collaborative networks, highly cited papers, and keywords to systematically understand the current status and trends of electrochemical disinfection. The results showed that between 2002 and 2022, 1171 publications related to electrochemical disinfection were published, with an exponential increase in the cumulative number of publications (y=17.518e0.2147x, R2= 0.9788). The publications covered 76 disciplines with many articles published in high-impact journals. However, the research power was characterized by a large number of scattered research efforts and insufficient cooperation, indicating the need for further innovative collaboration. The citation analysis and keyword analysis suggest that future development in this field may focus on optimizing electrode materials, investigating the disinfection performance of ·OH based systems, optimizing conditions for actual wastewater treatment, and reducing energy consumption to promote practical applications.

Test Dimensionality and Conditional Independence of Undergraduate Physics Test Items of National Open University of Nigeria: Perspective from Latent Traits Model (Ltm) Package of R Language

Physics test items developed by the National Open University of Nigeria (NOUN) to measure test-takers' proficiency in Elementary Mechanics, Heat, and Properties of Matter (PHY101) are intrinsically multidimensional. However, we observed the current method used by the University to score test-takers proficiency in the course is premised on Classical Test Theory, which has been criticised in the literature for its limitations, and a measurement model for unidimensional tests. Consequently, using an inappropriate model to model test-takers responses to items would adversely affect their true proficiency in the course. Therefore, this study assessed the dimensionality and conditional independence of physics test items of NOUN using the ltm package in the R language. A non-experimental design of survey research type was adopted. Test-takers responses to the 35 PHY 101 multiple-choice items across NOUN study centres in the 36 States of Nigeria were retrieved from the Directorate of Examination of Assessment (DEA) and used for the study, with empirical reliability of 0.80. Nine hundred seventy-eight test-takers responses were captured and analysed with modified parallel analysis test and Yen Q3 statistics implemented in ltm package of R language software, version 4.0.2. Findings remarked that NOUN physics items had more than one predominant dimension to account for the observed performance of test-takers in the course. Also, residual correlations of ten item pairs severely violated the conditional independence benchmark of 0.20. We conclude that PHY 101 of NOUN is intrinsically multidimensional. Test-takers responses to the test items are due to their locations on multiple latent variables. We recommend that a psychometric unit be established within the DEA of the University to check the appropriateness of the test items developed by the faculty lecturers.

Heuristics to Support the Evaluation of Optimal Experience in Educational Games for Learning Japanese as a Second Language

The evaluation of Computer-Assisted Language Learning (CALL) tools can be carried out from the perspective of different aspects, and there’s still no proposal from the literature for the evaluation of CALL games from the perspective of an “optimal experience”. Therefore, this paper proposes a set of 32 heuristics for the evaluation of educational games for Japanese Language Learning (JCALL). Furthermore, the heuristics were applied in the evaluation of JCALL L2 (i.e., as a second language) games in order to verify their usefulness. Findings show the heuristics provide good support in the evaluation of language learning educational games, and can collaborate in the redesign of these games in order to improve the optimal player experience. Finally, results also indicate the feasibility of using these heuristics in the evaluation of other types of CALL tools other than games.

Development of a Survival Nomogram for Esophageal Squamous Cell Carcinoma Patients: a Population-Based Analysis.

In this study, we developed a prognostic nomogram for esophageal squamous cell carcinoma (ESCC) patients. Patients diagnosed with ESCC from the Surveillance, Epidemiology, and End Results (SEER) database (1975-2017) and a local hospital were enrolled in this retrospective cohort study. Prognoses were analyzed using the R language software, and the predictive power of the model was then assessed by the Harrell concordance index (C-index) and the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. In total, 2915 ESCC patients from SEER database were divided into training and validation cohorts. Multivariate analysis revealed that sex, marital status, tumor-node-metastasis (TNM) stage, surgery, chemotherapy, and radiation all showed a significant association with overall survival (OS) and cancer-specific survival (CSS) (also with tumor grade). These characteristics were employed to build a nomogram. The C-index of the nomogram for OS and CSS prediction was 0.743 and 0.748 for the training cohort, which were superior to the predictive power of the 7th TNM staging system. The AUCs of the nomogram for predicting 2- and 5-year OS were 0.805 and 0.812, respectively, and the AUCs for CSS were 0.811 and 0.821, respectively. ROC and calibration curves of data from the SEER internal validation set and of data from our hospital showed that this model had good accuracy for predicting the prognosis of ESCC patient. The nomogram developed in this study provides a useful tool for accurately estimating OS and CSS for ESCC patients.

Teaching Strategies of English Speaking Informatization in Colleges and Universities in the Context of Computer-Assisted Language Learning

Abstract In order to improve the quality of teaching spoken English, this paper reconstructs the semantic structure through the weight matrix, and the association matrix describes the mapping process in the context of computer-assisted language learning. Pooling layer vectors are computed, and translation transformation matrices are encoded in real time so as to extract language vector features. Feature regression evaluation is implemented in a restricted Boltzmann machine to enhance the decoding language target through human-computer interaction, described using nonlinear functions, and the text to be translated is input to the deeply structured semantics, which is processed by weighted averaging to form a spatial vector to complete the input layer mapping process for the utterance. To verify the feasibility of this teaching model, the effectiveness of the teaching strategy is analyzed. The results showed that the variance of spoken English of college students with computer assistance was 0.534, the memory rate increased by at least 0.07, and the value of the number of words memorized by college students increased by more than 98.72%. It can be seen that the proposed information-based teaching model of spoken English in colleges and universities breaks the traditional education method and makes the teaching strategy approach more diversified.

4TH INDUSTRIAL REVOLUTION AND ARTIFICIAL INTELLIGENCE

An overview of industrial revolutions is made. Then the analysis of the fourth industrial revolution. The main major components of Industry 4.0 are identified, and their essence is revealed. The tasks of artificial intelligence within Industry 4.0 are also considered. Developed software in Python language about data and machine learning (ML) to visualize objects and table data. In order to use the capabilities of AI to the maximum benefit for business, it is necessary to hire data scientists. Data science combines statistics, computer science and business knowledge to extract value from various data sources. Developers use artificial intelligence to more effectively perform tasks that would otherwise have to be done manually, interact with customers, identify patterns and solve problems. To start working with AI, developers will need mathematical knowledge and the ability to use algorithms. There are several stages in the development and deployment of machine learning models, including training and inference. AI learning and inference refers to the process of experimenting with machine learning models to solve a problem. For example, a machine learning engineer can experiment with various candidate models to solve a computer vision problem, such as detecting bone fractures in X-ray images. Keywords: fourth industrial revolution, artificial intelligence.

SAT119 Artificial Intelligence Mediated Assistants: Will They Educate The Public About Health Disparities In Diabetes?

Abstract Disclosure: W. Zhao: None. G. Wu: None. E. Cheng: None. J. Lee: None. A. Wong: None. Background: In 2022, 37 million US adults had diabetes and 96 million had pre-diabetes. Diabetes and prediabetes affect 49.3% population in America. In the diabetic population, 12.1% are non-Hispanic blacks, 11.8% of Hispanics, and 9.5% of Asian Americans. 54% of Americans read at or below the sixth-grade level. ChatGPTTM, launched 11/30/22, has the newest Artificial Intelligence (AI) software versus Google AssistantTM, launched 05/2016. Purpose: Can ChatGPT use its natural language software to educate the lay public about diabetes and health disparities? Methods: Evaluate the readability of responses after five questions were posed to ChatGPTTM and Google AssistantTMQuestions: 1. Do African Americans have a higher risk of complications with Type 2 Diabetes? 2. Do Hispanic Americans have a higher risk of complications with Type 2 diabetes? 3. Do Asian Americans have a higher risk of complications with Type 2 diabetes? 4. Do women get Type 2 diabetes more than men? 5. What is pre-diabetes vs diabetes? Word count and Dale-Chall score assessed the readability level of both ChatGPT and Google Assistant responses. The Dale-Chall readability formula is calculated based on the percentage of difficult words and average sentence length in words. The U.S. Department of Education used the Dale-Chall formula to adjust the text to grade-level readability. Result: Word count: CHAT:Q1=104; Q2=135; Q3=136; Q4=133; Q5=232 vs GOOGLE: Q1=38, Q2=49, Q3=16; Q4=50; Q5=42. CHAT Word Count Avg=148, SD=48.81; GOOGLE Word Count Avg=39, SD=13.7; P-value=0.003908 Dale-Chall: CHAT: Q1=8.4; Q2=8.6; Q3=9.8, Q4=8.6, Q5=8.7 vs. GOOGLE: Q1=6.7, Q2=9, Q3=9.4, Q4=6.3, Q5=9.1. CHAT Dale-Chall Score Avg=8.82, SD=0.56; GOOGLE Dale-Chall Score Avg=8.1, SD=1.47; P-value=0.1306. ChatGPT has nearly the same grade level of comprehension as Google Assistant, including statistics about health disparities. However, ChatGPT was trained using information and transforming it into paragraphs, and google assistant extracts the data from websites and the variability is higher with a higher standard deviation than ChatGPT. Conclusion: ChatGPT with its artificial intelligence software is able to provide answers to our patients. While the answers may require a high school reading level and beyond, this is an excellent beginning for health education. Presentation: Saturday, June 17, 2023

A data assimilation method for blast load prediction

Blast load is a crucial parameter in blasting construction design and numerical simulation. However, it is characterized by dense energy, high loading rate and complex action process, which makes its accurate measurement difficult. In this study, based on experimental data-driven physical simulation, a data assimilation method for blast load prediction was proposed by integrating PFC2D software and Python language. The method can accurately measure the blast load, as it achieves an exact match between the numerical calculation results and the test far-field strain waves by automatically adjusting the peak blast pressure, rise/fall time and rock damping ratio. Furthermore, the effectiveness of the method was verified by performing rock blasting disturbance tests, and the superiority of the data assimilation algorithm was illustrated from two aspects, i.e., time-loading path and rock damping ratio. The following research results were obtained: 1) When the blast pressure is constant, the number of micro cracks within the rock decreases first and then increases with the rise of loading rate, while it always increases with the rise of unloading rate. Therefore, it is necessary to measure the time-loading path of blast pressure. 2) When the rock damping ratio deviates more notably from the true value, the error rate of the peak blast pressure by the assimilation method is greater correspondingly, indicating that the rock damping ratio is a prerequisite for accuracy of the assimilation method. 3) Superior to the traditional isentropic expansion theory, the assimilation algorithm not only accurately measures the peak blast pressure but also considers both the time-loading path and the rock damping ratio. The research results enrich rock dynamic tests and provide valuable references about blasting engineering.

KAṆIṈIYIL TAMIḺ MEṈPORUṬKAḶIṈ CEYALPĀṬUKAḶ [FUNCTIONS OF TAMIL SOFTWARE ON COMPUTERS

Today, computers and mobile phones are integrated in the daily life of people. It is a matter of pride that Tamil, our mother tongue, is featured in the computer. Computers and software are combined with the Tamil language to make the saying ‘sweetness and wateriness are Tamil’ true. Being the language of use in many countries, Tamil has earned a special place for itself. Tamil Literature, Language, Linguistics History, Nature of Language, cultural Elements Today, ideas are uploaded on computers and internet at various levels. These are very useful for Tamil language development to solve the problems of uploading Tamil language news on computer and internet; various Tamil language software’s have emerged. This review aims to reveal the functions of Tamil software such as computers, machine translation, Tamil font converters, grammar, and punctuation corrector, spell corrector, etc.

Survival prognosis model for elderly women with epithelial ovarian cancer based on the SEER database.

We aimed to analyze the risk factors of elderly women with epithelial ovarian cancer (EOC) using data on the SEER database, and to generate a nomogram model their 1-, 3-, and 5-year prognoses. The resulting nomogram model should be useful for clinical diagnoses and treatment. We collected clinical data of women older than 70 years with epithelial ovarian cancer (diagnosed on the basis of surgical pathology) from the SEER database including datasets between 2010 and 2019. We randomly grouped the data into two groups (7:3 ratio) using the R language software. We divided the independent prognostic factors obtained by univariate and multi-factor Cox regression analyses into training and validation sets, and we plotted the same independent prognostic factors in a nomogram model of overall survival (OS) at 1, 3, and 5 years. We used the C-index, calibration curve, and area under the curve to validate the nomograms. We further evaluated the model and its clinical applicability using decision curve analyses. We identified age, race, marital status, histological type, AJCC staging, differentiation degree, unilateral and bilateral tumor involvement, number of positive lymph nodes, chemotherapy, surgery, sequence of systemic treatment versus surgery, and time from diagnosis to treatment as independent prognostic factors for elderly women with EOC (P < 0.5). The C-indexes were 0.749 and 0.735 in the training and validation sets, respectively; the ROC curves showed that the AUC of each prognostic factor was greater than 0.7; and, the AUC values predicted by the line plot were similar in the training and validation sets. The decision curves suggest that this line plot model has a high clinical value for predicting overall survivals at 1, 3, and 5 years in elderly women with EOC. The nomogram model in this study can provide an accurate assessment of the overall survival of women older than 70 years with EOC at the time of the first treatment, and it provides a basis for individualized clinical treatment.