A Cross-Corpus Deep Learning Approach to Social Media Emotion Classification

Emotion Detection refers to the identification of emotions from contextual data in the form of written text, such as comments, posts, reviews, publications, articles, recommendations, conversations, and so on. Because of the Internet's exponential uptake and the recent coronavirus outbreak, social media platforms have become a crucial means of sharing thoughts and ideas throughout the entire globe, creating rapid data growth through users' contributions on various platforms. The necessity to acquire knowledge of their behaviors is a matter of great concern for both internet safety and privacy. In this study, we categorize emotional sentiments using deep learning models along with hybrid approaches such as LSTM, Bi-LSTM, and CNN+LSTM. When compared to existing state-of-the-art methods, the experiments showed that the suggested strategy is more robust and achieves an expressively higher quality of emotion detection with an accuracy rate of 94.16%, including strong F1-scores on complex and difficult emotion categories such as Fear (93.85%) and Anger (94.66%) through CNN+LSTM. © 2022 IEEE.

Digital Literacy Practices of Engineering Students Using E-Textbooks at a University of Technology in South Africa

South Africa's higher education system, like many others, is presently experiencing a significant transition towards digital forms of teaching and learning. This transition precedes the advent of Covid-19 but has been hastened by the pandemic. However, these new technologies also bring with them new digital practices. A crucial means by which communication is enacted is by reading e-textbooks. However, e-textbooks may enable different forms of engaging with written text than are offered by traditional, print textbooks. Despite this need, only a few studies have been conducted on students' use of e-textbooks in engineering education. In this study, data were collected by way of focus-group interviews conducted with first-year students from two engineering departments (chemical engineering and nautical science) at a university of technology in South Africa. The data were analyzed using thematic content analysis using ATLAS.ti. In order to analyze and contextualize the findings obtained, the researchers make use of a theoretical framework, Mediated Discourse Analysis (MDA). The findings provide insight into how students engage with e-textbooks and how this might be different from engaging with traditional, print textbooks. The findings also reveal the extent to which some new digital literacy reading practices remain unfamiliar to engineering students. © 2022 IEEE.

High-Quality Text Descriptions of Visual Elements in Online Interactive Versions of Traditional Print Mechanical Engineering Textbooks

Even before the Covid-19 pandemic, there was an increased utilization of online course materials. Circumstances created by the pandemic increased the need for high quality online course content. These online course materials should comply with accessibility regulations and guidelines to provide an equal learning experience for all students. Although these guidelines describe broad requirements, specific standards for creating text descriptions of visual elements, both static and interactive, have yet to be created for mechanical engineering content. Research is lacking regarding accessibility of images and other visuals within online interactive mechanical engineering texts. Defining standards for how engineering visual elements like images and animations are textually described will provide a baseline to measure the effectiveness of visual elements for students who require assistive technology, such as screen readers. The goal of this paper is to define accessibility standards developed for textually describing images, figures, graphs, animations, and other visual elements for a series of online interactive mechanical engineering textbooks (zyVersions) that have been adapted from traditional print textbooks. The group of content authors working on these zyVersions have written text descriptions (alt text) for the visual interactive content (animations) that have been added to the traditional textbook and in many cases have added to the text descriptions for figures including images, equations, and graphs that already appeared in the print text. The standards that have been used by this team of content authors include: (1) Writing text that balances precision with conciseness;(2) Structuring alt text to first capture important information, then incrementally filling in finer details;(3) Well-defined procedures for describing certain types of visual elements, such as phase diagrams and phase transformation plots in materials science and engineering, T-s, h-s, and P-v diagrams in thermodynamics, output response plots in control systems, as well as other common visual elements in mechanical engineering courses;and (4) Writing text for animated visual elements that describe in detail all dynamic processes and movements in the animation. This paper describes our guidelines in detail, and presents examples from three different zyVersions used in mechanical engineering courses. These standards can be modified for use across various engineering disciplines and will enable authors of online content to provide higher quality material that meets accessibility standards. © American Society for Engineering Education, 2022