English Semantic Similarity based on Map Reduce Classification for Agricultural Complaints

Rslan, Esraa; Khafagy, Mohamed Helmy; Munir, Kamran; Badry, Rasha M.

doi:10.14569/ijacsa.2021.0121231

Cited by 4 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This second output (output 2) of the proposed model will also provide the value of TF-IDF, which represents the weight of a text "i" in a tweet "j". As indicated in [28] TF-IDF provides the best performance of Fscore approximately 77.8%~94.8%, compared to other approaches, so its use guarantees the functionality of your application in determining the most relevant aspects of the satisfaction.…”

Section: Conditioning Sentiment Polarization Analysis and Data Extrac...mentioning

confidence: 98%

“…Similarly, in [14] it is indicated that there is a significant improvement in Fscore when the data set is used after removing stopwords, so it is shown that the impact of removing stopwords is greater in TF-IDF than in TF-IDF that of fasttext. Likewise, in [28] it is pointed out that TF-IDF provides the best performance in determining the most relevant aspects of satisfaction. This was reflected in its results, where the system made an F score with 0.939 using TF-IDF, then around 0.899 in the TF, due to this, it is indicated that the system will be fast and reliable.…”

Section: Conditioning Sentiment Polarization Analysis and Data Extrac...mentioning

confidence: 99%

“…SA, is an area of NLP, focuses on detecting, extracting, analyzing and classifying opinions, sentiments, evaluations and emotions published on different social networks (Facebook, Twitter, LinkedIn, among others) towards certain organizations or organizations people [27]. As indicated in [28] sentiment analysis seeks to extract an opinion and determine its polarity (positive, negative or neutral). Likewise, in [29], [30] it is pointed out that being the social network Twitter one of the most commonly used tools to determine the opinions of users about a wide variety of topics, this is not unrelated to the fact that, in the environment educational, sentiment analysis is used to evaluate student performance, teacher performance, academic desertion, among other relevant issues that aim to improve educational quality.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Text mining and sentiment analysis of teacher performance satisfaction in the virtual learning environment

Chamorro-Atalaya

Arce-Santillan

Arévalo-Tuesta

et al. 2022

IJEECS

View full text Add to dashboard Cite

Although it is true that artificial intelligence and data science have become key tools that contribute to the improvement of many processes, identifying patterns and contributing to decision making, however, there are environments in which they are not yet being using it relevantly and effectively. The objective of this study is to identify the relevant factors, based on the opinions expressed by the students through the social network Twitter regarding the perception of satisfaction with the teaching performance during the virtual learning environment. For which sentiment analysis and text mining are used under the Python programming language environment, through JupyterLab. As results, it was determined that a predominance of 57.27% of positive polarity, identifying that the relevant factors of student satisfaction with teaching performance, are related to the development of the teacher in the class sessions that contributes to the learning of the process control subject through the use of simulation tools such as simulink and tools linked to proportional integral derivative (PID) controllers; on the other hand, there is a percentage of negative polarity of 15.45% that belongs to the factors linked to the laboratory sessions in which graphic representation and block diagrams were used to explain the class session.

show abstract

Section: Conditioning Sentiment Polarization Analysis and Data Extrac...mentioning

confidence: 98%

Section: Conditioning Sentiment Polarization Analysis and Data Extrac...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Text mining and sentiment analysis of teacher performance satisfaction in the virtual learning environment

Chamorro-Atalaya

Arce-Santillan

Arévalo-Tuesta

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…Word vectors are created after preprocessing and classifying the farmer text and agriculture dataset. Then, we apply LSA [29], [30] to calculate the semantic similarity between the farmer text and the available agriculture dataset. LSA is a powerful corpus-based technique for calculating semantic similarity.…”

Section: Applying Lsamentioning

confidence: 99%

AgroSupportAnalytics: big data recommender system for agricultural farmer complaints in Egypt

Rslan

Khafagy²,

Ali³

et al. 2023

IJECE

View full text Add to dashboard Cite

<span>The world’s agricultural needs are growing with the pace of increase in its population. Agricultural farmers play a vital role in our society by helping us in fulfilling our basic food needs. So, we need to support farmers to keep up their great work, even in difficult times such as the coronavirus disease (COVID-19) outbreak, which causes hard regulations like lockdowns, curfews, and social distancing procedures. In this article, we propose the development of a recommender system that assists in giving advice, support, and solutions for the farmers’ agricultural related complaints (or queries). The proposed system is based on the latent semantic analysis (LSA) approach to find the key semantic features of words used in agricultural complaints and their solutions. Further, it proposes to use the support vector machine (SVM) algorithm with Hadoop to classify the large agriculture dataset over Map/Reduce framework. The results show that a semantic-based classification system and ﬁltering methods can improve the recommender system. Our proposed system outperformed the existing interest recommendation models with an accuracy of 87%.</span>

show abstract

“…There are two measures of knowledge-based similarity that are semantic similarity and semantic relatedness. While in corpus-based similarity, it is a semantic similarity metric that determines how similar two terms are which is based on the large corpora's information such as HAL, LSA, ESA, and NGD [2,4,5]. In this research, the corpus-based similarity is the focus research similarity metric, especially the use of Latent Semantic analysis LSA.…”

Section: Introductionmentioning

confidence: 99%

Automatic Arabic Grading System for Short Answer Questions

et al. 2023

Self Cite

View full text Add to dashboard Cite

The era of technology and digitalization has been advantageous to the educational sector.The examination system is one of the most important educational pillars that have been affected. As automatic exam grading is a revolution in the history of exam development, and therefore the automatic grading system has started to replace the traditional assessment system. The automatic grading system allows the examiners to automatically assign grades for students'' answers compared to the model answers. And, generate results based on the examiners' answers. In this paper, we especially address the short answer questions. Most research has been done on the English language. On the other side, few research works have been conducted on Arabic. Moreover, Arabic is considered one of the rare resource languages. This paper is aimed to build an Automatic Arabic Short Answer Grading (AASAG) model using semantic similarity approaches. It is used to measure the semantic similarity between the student and model answer. The proposed model is applied to one of the Arabic scarce publicly available datasets which is called (AR-ASAG). It contains 2133 pairs of models and student answers in several versions such as txt, xml, and db. The efficiency of the proposed model was evaluated through two conducted experiments using two weighting schemas local, and hybrid local and global weighting schema. The developed approach with hybrid local and global weight-based LSA achieved better results than using local weight-based LSA with (82.82%) as F1-score value, and 0.798 as an RMSE (Root-Mean-Square Error) value using hybrid local and global weight-based LSA.INDEX TERMS Short Answer Grading system, Arabic language, global weight-based LSA

show abstract

English Semantic Similarity based on Map Reduce Classification for Agricultural Complaints

Cited by 4 publications

References 17 publications

Text mining and sentiment analysis of teacher performance satisfaction in the virtual learning environment

Text mining and sentiment analysis of teacher performance satisfaction in the virtual learning environment

AgroSupportAnalytics: big data recommender system for agricultural farmer complaints in Egypt

Automatic Arabic Grading System for Short Answer Questions

Contact Info

Product

Resources

About