​Student Work

Their Work SPARKLES!

Title: Disaster Detector on Twitter Using Bidirectional Encoder Representation from Transformers with Keyword Position Information

Abstract: Deep learning, as one of the most currently remarkable machine learning techniques, has achieved great success in many applications such as image analysis, speech recognition, and text understanding. This work aims to make use of the bidirectional encoder representation from transformers (BERT) model to a particular problem in our real life, detecting disaster on Twitter. Specifically, we first validate the practicability of BERT in disaster detection, and then improve the model practicability by extracting keyword information to classify the text. The experimental results show that our method achieves a more accurate prediction of texts announcing a disaster compared to the models without keyword position information. The result of this research will be helpful in monitoring and tracking social media content and in discovering how people's descriptions of disasters are like.

Z. Wang, T. Zhu and S. Mai, "Disaster Detector on Twitter Using Bidirectional Encoder Representation from Transformers with Keyword Position Information," 2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT, 2020, pp. 474-477, doi: 10.1109/ICCASIT50869.2020.9368610.

Title: Epidemic Case Prediction of COVID-19: Using Regression and Deep based Models

Abstract: COVID-19, as an international concern of public health emergency, carries the property of high death and infection rates. Researchers need to give an accurate prediction of the daily increase in COVID-19. Though the 2002-2003 SARS breakout provides prescient guidance for these issues, there exist two bottlenecks. First, traditional models that are popular during the SARS period are not able to fit the trend of COVID-19 and predict the cases effectively. Second, the worldwide spreading of COVID-19 also causes the traditional model to fail its function. In this study, we apply several regression models and deep based models for prediction of the COVID-19 pandemic. We perform L1-norm to compute feature-selection; besides, we also introduce SIR, SEIR models to improve our model accuracy. Then, we measure the accuracy of models by Mean Squared Error(MSE). This study concludes that the SEIR model is the best model with the highest performance among the tested approaches.

Z. Wang, T. Zhu and S. Mai, "Disaster Detector on Twitter Using Bidirectional Encoder Representation from Transformers with Keyword Position Information," 2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT, 2020, pp. 474-477, doi: 10.1109/ICCASIT50869.2020.9368610.

Title: The Understanding of Major Depressive Disorder: a Multidimensional Analysis from Evolution to Cognitive Neuroscience

Abstract: From the 19th to 20th century, many different approaches to mental disorder topic have been published to promote a more informative and comprehensive understanding of Major Depressive Disorder (MDD). However, previous studies on MDD had gone in-depth on a specific area, but failed to combine the understanding of MDD in other areas. The areas include evolutionary, genetic, hormones, brain structures, brain function, and early childhood trauma. Specific inferences are drawn as to how and in what ways these areas approach on mental disorder help to solve the mystery of major depressive disorder. This article is focusing on a variety of perspectives of Major Depressive Disorder (MDD) that mentioned above and helps to educate readers who are unfamiliar with this type of mental disorder. With the joint efforts of scholars in various fields, the mental health community will have huge success in defending mental disorder.

B. Xiao, “The Understanding of Major Depressive Disorder: a Multidimensional Analysis from Evolution to Cognitive Neuroscience,”2020 3rd International Conference on e-Education, e-Business and Information Management, EEIM, 2020, pp. 115-120, DOI: 10.23977/EEIM2020023.

Title: Online Harassing in Chinese Societies – Association among Harassing Behaviors, Misinformation and General Prevalence

Abstract: This Online harassment has become a popularized form of assault in China and has

caused many traumas to the current generation; however, research of online harassment in China is still in an early stage. In this study, we aimed to observe the prevalence of online harassment in Chinese mainland, and to examine the association between harassing behaviors and relevant offensive behaviors. Our topics and discussions mainly focused on fake information and related impacts. We recruited 959 participants who are Chinese citizens in different age groups located in different parts of Chinese mainland. They were asked to completed an online questionnaire consisted of 29 multiple-choice questions designed by the Pew Research center with the SRBI inc. in September 2020. Data of participants’ personal harassing experience and opinions toward certain behaviors were collected, with several nominal factors such as gender presented. In this study, 94.68% (n=908) of the participants reported that they have been harassed online, and 5.32% (n=51) reported that they never had such experience. Specifically, purposeful embarrassment was the most common form of online harassing behaviors, with ~18% (n=333) of the victims reported. Besides, 63.92% of the participants reported that others have posted fake information about them on the Internet, with the majority of the fake information focused on victim’s reputation and job performance. In addition, no association was found between phone usage and the possibility of having someone post misinformation of users. Online harassment is a common experience of Chinese citizens, as many reported that they had such experience. Our study complemented on the researches of online harassment in Chinese mainland, and emphasized the urgent need for more regulations and policies to prevent online harassment.

B. Liu, and Y. Ke, “Online Harassing in Chinese Societies – Association among Harassing Behaviors, Misinformation and General Prevalence,” 7th International Symposium on Social Science (ISSS 2021), 2021, pp. 68-78, DOI: 10.26914/c.cnkihy.2021.004323.