AI-based production and application of English multimode online reading using multi-criteria decision support system

Dong, Yifan; Yu, Xinyu; Alharbi, Abdullah; Ahmad, Sultan

doi:10.1007/s00500-022-07209-2

Cited by 14 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With supervised training, the data cost involved in model training is high. erefore, further improvements to the summary generation models based on recurrent neural networks and their variants are needed [27][28][29].…”

Section: Related Workmentioning

confidence: 99%

XAI-Based Reinforcement Learning Approach for Text Summarization of Social IoT-Based Content

Abdeljaber

Ahmad

Alharbi

et al. 2022

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

The purpose of automatic text summarising technology is to condense a given text while properly portraying the main information in the original text in a summary. To present generative text summarising approaches, on the other hand, restructure the original language and introduce new words when constructing summary sentences, which can easily lead to incoherence and poor readability. This research proposes a XAI (explainable artificial intelligence)-based Reinforcement Learning-based Text Summarization of Social IoT-Based Content using Reinforcement Learning. Furthermore, standard supervised training based on labelled data to improve the coherence of summary sentences has substantial data costs, which restricts practical applications. In order to do this, a ground-truth-dependent text summarization (generation) model (XAI-RL) is presented for coherence augmentation. On the one hand, based on the encoding result of the original text, a sentence extraction identifier is generated, and the screening process of the vital information of the original text is described. Following the establishment of the overall benefits of the two types of abstract writings, the self-judgment approach gradient assists the model in learning crucial sentence selection and decoding the selected key phrases, resulting in a summary text with high sentence coherence and good content quality. Experiments show that the proposed model's summary content index surpasses text summarising ways overall, even when there is no pre-annotated summary ground-truth; information redundancy, lexical originality, and abstract perplexity also outperform the current methods.

show abstract

Section: Related Workmentioning

confidence: 99%

XAI-Based Reinforcement Learning Approach for Text Summarization of Social IoT-Based Content

Abdeljaber

Ahmad

Alharbi

et al. 2022

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, these services are usually expensive. AI-based writing tools (e.g., ChatGPT, GPT4, LLaMA series, ChatGLM series, PaLM series, Gemini, AlphaGo, Inflection, and Falcon) can facilitate scientific writing [165,166] but it is important to note that AI-based tools should not replace real authors or human creativity. As a result, journals such as Nature and Science have banned the inclusion of these AI tools as co-authors or their direct use for generating papers or assignments [167].…”

Section: Artificial Intelligence-based Research In Soil Sciencementioning

confidence: 99%

Trends in Soil Science over the Past Three Decades (1992–2022) Based on the Scientometric Analysis of 39 Soil Science Journals

Jia,

Wang,

Zvomuya

et al. 2024

Agriculture

View full text Add to dashboard Cite

As one of the basic disciplines of agricultural, natural resource, and environmental science, soil science has played a critical role in global food security and socio-economic and ecological sustainability. The number of soil science journals and publications has increased remarkably with the development of soil science. However, there is a lack of systematic and comprehensive studies on the developmental trends of soil science based on journals and publications. In this study, 39 journals included under the soil science category in the 2022 Journal Citation Reports, and 112,911 publications in these journals from 1992 to 2022 were subjected to scientometric/bibliometric analysis to determine trends in publication, journal metrics, co-authorship, and research topics, in addition to general journal information. The results show that soil science ushered in a renaissance period with the number of publications, citations, impact factors, and CiteScore demonstrating an increasing trend. America and the Chinese Academy of Sciences had the most publications and citations. The most productive author published more than 400 articles. Soil science research focused mostly on its fundamental impact on the ecological environment based on the strongest citation bursts analysis of keywords. The analysis indicated that open access has increased in popularity. Current soil science journals still face a few common challenges, including an urgent need for a fairer evaluation mechanism on journal quality compared to the traditional use of single metrics as well as equity, diversity, and inclusion (EDI) in the whole editorial process. Artificial intelligence may bring new tools and more changes to the development of soil science. This study will help soil science researchers to better understand the development status and future trends of soil science. It will also guide authors in journal selection.

show abstract

“…In the context of sustainable English education, manual grading will not only add unnecessary burden to the grading teachers, but also bring some adverse effects. Therefore, intelligent grading is gradually widely used [2]. Zhou built an automatic composition scoring system under the mixed mode of English writing on the basis of machine learning (ML) for the related problems of manual grading [3].…”

Section: Introductionmentioning

confidence: 99%

Research on the Application of Intelligent Grading Method based on Improved ML Algorithm in Sustainable English Education

Huang,

2024

SCPE

View full text Add to dashboard Cite

The current intelligent grading methods in English education have issues of feedback lag and incompatibility with manual grading, and manual grading is easily influenced by subjective consciousness. Based on this, this research selects Adaboost algorithm in ML algorithm to realize intelligent grading. The experiment improves the Adaboost algorithm according to the actual needs, constructs the Adaboost/CT algorithm, and verifies its effectiveness. The experimental results show that in the English intelligent scoring module, the adjacency accuracy of the Adaboost/CT algorithm for high- and low-quality English is 95.33%; 95.45% in the middle score; 94% in the breakdown. The comparison between Adaboost/CT model and DFA method shows that the accuracy and proximity accuracy of Adaboost/CT are 79.66% and 94% respectively, which are much higher than 55% and 92% of DFA. In addition, compared with Adaboost, the accuracy of Adaboost/CT is also significantly better than Adaboost. In practical application, the use of Adaboost/CT in the evaluation of English compositions can not only get more accurate scores, but also find out the shortcomings of each student, so as to improve them pertinently. Meanwhile, the accuracy, recall, and F1 values of the Adaboost/CT algorithm are 96%, 95%, and 95%, respectively, which are higher than those of the comparison algorithm. Overall, the improved Adaboost/CT algorithm has shown high effectiveness and practicality, and has high applicability and effectiveness in practical intelligent grading.

show abstract

AI-based production and application of English multimode online reading using multi-criteria decision support system

Cited by 14 publications

References 44 publications

XAI-Based Reinforcement Learning Approach for Text Summarization of Social IoT-Based Content

XAI-Based Reinforcement Learning Approach for Text Summarization of Social IoT-Based Content

Trends in Soil Science over the Past Three Decades (1992–2022) Based on the Scientometric Analysis of 39 Soil Science Journals

Research on the Application of Intelligent Grading Method based on Improved ML Algorithm in Sustainable English Education

Contact Info

Product

Resources

About