Analysis using natural language processing of feedback data from two mathematics support centres

Cronin, Anthony; İntepe, Gizem; Shearman, Donald; Sneyd, Alison

doi:10.1080/0020739x.2019.1656831

Cited by 9 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In CountVectorizer, the number of times a word occurs in a document is counted [37]. It provides a very lucid way to tokenize the set of text documents along with building a vocabulary of the known words as well as the encoding of fresh documents by making use of that particular vocabulary [38][39][40]. In TfidfVectorizer, the overall weightage of a word occurring in a document is considered [41].…”

Section: Nlp Algorithms and Techniques Employed Naturalmentioning

confidence: 99%

Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

Gupta

Wu²,

Arora

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

A cancer tumour consists of thousands of genetic mutations. Even after advancement in technology, the task of distinguishing genetic mutations, which act as driver for the growth of tumour with passengers (Neutral Genetic Mutations), is still being done manually. This is a time-consuming process where pathologists interpret every genetic mutation from the clinical evidence manually. These clinical shreds of evidence belong to a total of nine classes, but the criterion of classification is still unknown. The main aim of this research is to propose a multiclass classifier to classify the genetic mutations based on clinical evidence (i.e., the text description of these genetic mutations) using Natural Language Processing (NLP) techniques. The dataset for this research is taken from Kaggle and is provided by the Memorial Sloan Kettering Cancer Center (MSKCC). The world-class researchers and oncologists contribute the dataset. Three text transformation models, namely, CountVectorizer, TfidfVectorizer, and Word2Vec, are utilized for the conversion of text to a matrix of token counts. Three machine learning classification models, namely, Logistic Regression (LR), Random Forest (RF), and XGBoost (XGB), along with the Recurrent Neural Network (RNN) model of deep learning, are applied to the sparse matrix (keywords count representation) of text descriptions. The accuracy score of all the proposed classifiers is evaluated by using the confusion matrix. Finally, the empirical results show that the RNN model of deep learning has performed better than other proposed classifiers with the highest accuracy of 70%.

show abstract

Section: Nlp Algorithms and Techniques Employed Naturalmentioning

confidence: 99%

Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

Gupta

Wu²,

Arora

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…It involves tallying the occurrences of each word within a document [60]. Count vectorizer offers a clear method for tokenizing a set of text documents, creating a vocabulary of known words, and encoding new documents using that vocabulary [5,17,23].…”

Section: Feature Transformation or Feature Extractionmentioning

confidence: 99%

Multi-Class Classification of Genetic Mutation Using Machine Learning Models

Ankrah,

Brew,

Acquah

2024

Computational Journal of Mathematical and Statistical Sciences

View full text Add to dashboard Cite

The challenge of distinguishing genetic mutations that contribute to tumor growth is crucial in cancer treatment. Cancer is responsible for millions of deaths annually, hence the need for early detection of tumors to improve treatment efficacy and survival rates. However, manual classification is prone to errors and inefficiencies due to human limitations and the complexity of domain knowledge, leading to time-intensive processes. In response, machine learning models improve accuracy and efficiency for cancer prognosis and prediction. However, the lack of theoretical understanding of algorithms may limit the interpretability and applicability of results, where insights into model prediction are crucial to making informed decisions, especially in the biomedical domain. To address these challenges, our study employed four supervised machine learning algorithms, namely Support Vector Machine (SVM), Naïve Bayes (NB), Logistic Regression (LR), and Random Forest (RF). The performance of these algorithms was assessed using log-loss and misclassification rates. Logistic regression emerged as the optimal classifier with a log loss of 1.0125 and a misclassification rate of 30.97%.

show abstract

“…There is a wide variety of other forms of MSS including bridging courses, supplementary instruction and workshops, pre-assessment problem-solving workshops, small group sessions, student worksheets, commercial online tutoring programmes, online revision modules, online question and answer services and the use of internet resources (Bressoud et al, 2015;Grove et al, 2020;Jackson, 2020;Johns & Mills, 2021;Lawson et al, 2020;Rylands & Shearman, 2018). Some support is embedded within teaching (Grove et al, 2020) and indeed informs teaching (Cronin, 2019;Cronin et al, 2019;Cronin & Meehan, 2020).…”

Section: Mathematics and Statistics Supportmentioning

confidence: 99%

The rapid move to online mathematics support: changes in pedagogy and social interaction

Mullen

Pettigrew

Cronin

et al. 2021

International Journal of Mathematical Education in Science and

Self Cite

View full text Add to dashboard Cite

The dramatic changes brought on by the COVID-19 pandemic have changed the way in which mathematics and statistics support is offered. Students and staff have been presented with new opportunities and challenges. One-on-one interviews were conducted late in 2020 with 23 students and staff who had experience with fully online mathematics and statistics support. The interviewees were from University College Dublin, Ireland, and Western Sydney University, Australia. Utilising thematic analysis, five themes around online mathematics and statistics support common to both universities were identified. In this paper the three themes related to connection are explored; they are pedagogical changes, social interaction, and appreciation of mathematics and statistics support. These themes highlight the need felt by both students and staff for mutual connection. The paper concludes with a discussion on the repercussions of this study for future considerations of effective online mathematics and statistics support.

show abstract

Analysis using natural language processing of feedback data from two mathematics support centres

Cited by 9 publications

References 8 publications

Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

Gene Mutation Classification through Text Evidence Facilitating Cancer Tumour Detection

Multi-Class Classification of Genetic Mutation Using Machine Learning Models

The rapid move to online mathematics support: changes in pedagogy and social interaction

Contact Info

Product

Resources

About