Faculty

Education

Supervisor Name

Mi Song Kim

Keywords

Teaching Analytics, Topic Modelling, ML

Description

Our teaching analytics tool, is a responsive web application that consists of three main sections. The topic modelling section consists of the determination of main topics and topic relationships within text data such as class discussions or research articles through a Linear Discriminant Analysis (LDA) machine learning model. Initial data undergoes a number of preprocessing steps including removal of duplicates and outliers, lemmatization, and filtering by frequency and Term Frequency - Inverse Document Frequency (TF-IDF) scores before various visualizations are created. These visualizations include the identified topics and top words within each topic, a topic network graph for displaying interactions between topics, and word clouds highlighting the most frequent words per topic.

Currently, there are no public tools for extracting the content of OWL forums into well-formatted .csv files. Given that data analysis has become increasingly important in the field of educational studies, we have developed such a tool using the Python programming language. Our tool allows users to upload the html webpage of an OWL forum for which they would like to parse its data and get back a downloadable .csv file which can be opened easily with Microsoft Excel.

In addition, we took the project one step further and developed a machine-learning model that attempts to predict the emotional state of students given the content of their forum posts so that educators can receive feedback and tailor their curriculum to meet the expectations of students.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Document Type

Event

Included in

Education Commons

Share

COinS
 

Multimodal Teaching and Learning Analytics

Our teaching analytics tool, is a responsive web application that consists of three main sections. The topic modelling section consists of the determination of main topics and topic relationships within text data such as class discussions or research articles through a Linear Discriminant Analysis (LDA) machine learning model. Initial data undergoes a number of preprocessing steps including removal of duplicates and outliers, lemmatization, and filtering by frequency and Term Frequency - Inverse Document Frequency (TF-IDF) scores before various visualizations are created. These visualizations include the identified topics and top words within each topic, a topic network graph for displaying interactions between topics, and word clouds highlighting the most frequent words per topic.

Currently, there are no public tools for extracting the content of OWL forums into well-formatted .csv files. Given that data analysis has become increasingly important in the field of educational studies, we have developed such a tool using the Python programming language. Our tool allows users to upload the html webpage of an OWL forum for which they would like to parse its data and get back a downloadable .csv file which can be opened easily with Microsoft Excel.

In addition, we took the project one step further and developed a machine-learning model that attempts to predict the emotional state of students given the content of their forum posts so that educators can receive feedback and tailor their curriculum to meet the expectations of students.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.