Social Sciences – Page 33 – UROP Spring Symposium 2021

Social Sciences

Improving Student Mastery through Question Interleaving

Our research focuses on improving student masteries through question interleaving. Although previous researches by Rohrer and Taylor have shown that interleaving questions enhances student learning, there has been little research on question recommendation models that utilizes this concept to maximize student learning. We assume that question interleaving helps student learning. We aim to identify metrics that allow us to optimize the ordering of question interleaving and build a question recommendation model based on our findings. We are utilizing two datasets from online tutoring platforms that contain questions answered by students to analyze if our proposed metrics are statistically significant to base decisions on. We will also run simulations with Python on potential recommendation algorithms to see how well the result matches with a simple student ability model. The result of our findings aim to provide a question recommendation method that only relies upon the concept a question tests, but can be used in conjunction with further information. We hope our findings will align with our goal of having a question recommendation model that maximizes student learning. This allows for personalization in intelligent tutoring systems even before significant amounts of student/question data has been generated. The ultimate goal/implication of our research is to help improve learning results for all students simply by changing the order of their practice questions, without increasing their workload.

Improving Student Mastery through Question Interleaving Read More »

Information Geometry: Unified Framework for Information, Machine Learning, and Statistical Inference

This study aims at computing around KL-divergences of probability density distributions around different metrics. We try to compute 2nd/3rd derivatives for different metrics, affine connections and levi-civita Connections in particular, under these distributions in order to have an idea about the flatness of the different spaces we are working on. Given the nature of this independent study, most of these computations and results have already been proven before. We computed KL divergences, Jacobian and Fisher matrices under different metrics. We then derive some integral forms for Fisher Information matrices, affine connections, dual connections and derivative forms for coordinate transformation for these parameters. We found out that for metrics in exponentials, the affine connections turn out to be 0 everywhere, while in expectation coordinates, the dual connections are 0. This means that in either case, we are working with a flat space. Nothing spectacular has been found out around the normal metric(namely, (mean, standard deviation)).

Information Geometry: Unified Framework for Information, Machine Learning, and Statistical Inference Read More »

Developing fast and unbiased computer vision algorithms

Computer Vision Algorithms are a fast-developing technology, and we have seen from example that they are currently not as accurate and unbiased as we hope they can be. Our project aims to develop a more efficient system and algorithm to reduce bias in computer vision programs. One way bias may be introduced into these algorithms is through issues with light levels in images and videos. Since many computer vision algorithms rely on video cameras, as opposed to infrared or another type of light, the lack of light in videos introduces uncertainty in a program, which can produce bias, where some categories of images are more accurately processed by the algorithm than others. This bias can manifest itself in different scenarios, such as during nighttime or when recording people with darker skin, and these are the biases that we aim to correct. My part in the project involved labelling the videos that are going to be used for analysis for the algorithms, and attempting to help create a standardized method of labelling in order to have a set of videos with which the algorithm can be trained with. Our sample set was purposefully selected to have a variety of videos with different light levels and skin tones. Our ultimate purpose was to label as many videos as possible to use later on in the project, where other groups are working on developing the algorithm and all other overarching parts of the project. The main project was not completed, and likely will not for some years, but we achieved our loose goal of labelling videos.

Developing fast and unbiased computer vision algorithms Read More »

Developing fast and unbiased computer vision algorithms

In an effort to improve driver safety and autonomous vehicle testing, video recordings of drivers allow for data to be analyzed. These videos are first examined by human coders, but a more efficient, automated algorithm would prevent the need for human coders entirely. However, in order to build the algorithm, human coders need to analyze videos of drivers and label various actions, such as if the driver is turning or tilting their head, or hand movements, such as texting, and if their hand is obscured. Once these labels are implemented, they are tested against each other for accuracy, so that the final algorithm is unbiased enough to be implemented into vehicle safety.

Developing fast and unbiased computer vision algorithms Read More »

Developing Fast and Unbiased Computer Vision Algorithms

The research project I am participating in is “Developing Fast and Unbiased Computer Vision Algorithms” through the Multidisciplinary Design Program and the Transportation Research Institute. We’re trying to make a computer vision algorithm that could detect if drivers are paying attention to the road or distracted such as being on their phones. The algorithm itself should be as efficient and reliable as possible. To get our results, we look at frames of videos of people driving and create data sets and coding logs based on what the driver is doing. We have multiple people log the videos to create a benchmark of what the driver is doing. We also change our operational definitions of what we are looking for in the videos. The coding logs give us a benchmark for the algorithm so it can accurately judge what actions are distracted driving. By changing the variables we’re analyzing and improving the benchmark, we can make the algorithm more efficient, especially when we have a lot of different types of videos with varying lighting, subjects, and difficulty. Our research is vital because while transportation safety is important and an accurate algorithm detection distracted driving could help reduce the number of car accidents and car deaths, on a larger scale, our improvements of this computer vision algorithm would help improve how computer vision algorithms are created and applied in general. Overall, computer vision algorithms have shown to be biased especially with variables like skin color, sex/gender expression, and lighting. Those variables negatively affect the accuracy of the algorithm. Through our research, we could use our same methods and data to help other computer vision algorithms become more accurate and efficient.

Developing Fast and Unbiased Computer Vision Algorithms Read More »

Racial Bias in Medical School Admissions

Currently, the diversity of doctors and healthcare workers is not matching the increasing diversity of Americans (Boscardin, 2015). This lack of diversity contributes to health inequities – many patients of color avoid hospital visits because they feel as if they will not be listened to. In fact, it is proven that Latinx people and African American people utilize healthcare less, even when they have adequate access to healthcare (Ashton, 2003). Additionally, White clinicians may have a negative internal bias (e.g., implicit bias) towards patients of color which affects their treatment decisions. Research (e.g. Steiner, 2013) demonstrates that BIPOC physicians are less likely to have internal biases towards patients of color. Other research (e.g., Dennis, 2001) indicates that African American physicians are four times as likely to provide care to patients of color. Therefore, by increasing the diversity of healthcare professionals, patients of color will be more likely to receive the treatments they need, resulting in the reduction of some healthcare inequities. Diversity in the physician workforce can be facilitated by increasing the number of BIPOC students that are admitted to, and retained in, medical school. However, students of color may be discouraged from pursuing a career in medicine due to racial bias. My review focuses on various types of racial biases that BIPOC applicants face in the admissions process. Across the 15 articles I reviewed, I found that racial bias can occur in many critical stages: during reviews of application materials and letters of recommendation, applicant interviews, and the interpretation of MCAT scores. Additionally, I reviewed articles to identify some strategies that medical schools might implement to minimize the effect of racial bias. I discuss the implications of these studies, and future strategies that medical schools should take to combat racial bias.

Racial Bias in Medical School Admissions Read More »

The COVID-19 pandemic and mental health among those with pre-existing depression

Background. It has been a year since the COVID-19 pandemic began influencing broad social and economic factors, likely taking a toll on the mental health of many individuals. Those with pre-existing symptoms of hopelessness, anhedonia, and suicidal ideation that are characteristic of depression may be especially vulnerable to the effects of the COVID-19 pandemic on mental health. Previous research has shown that pre-existing psychopathology is a predictor of negative mental health consequences following traumatic events. However, other work indicates that those with depression can be resilient to stressful life events. Objective. The goal of this project was to review existing literature to determine the potential for the COVID-19 pandemic to influence mental health among those with pre-existing depression. Population of interest. Those with depressive symptoms or a depressive disorder prior to the onset of the COVID-19 pandemic.

The COVID-19 pandemic and mental health among those with pre-existing depression Read More »

Mental Health During COVID-19: The Effects on Suicidality

Objective: Various studies indicate that the COVID-19 pandemic has profoundly worsened community and individual well-being around the world. Of these psychological effects, rates of depression, anxiety, post-traumatic stress, insomnia, and suicidality have been rapidly increasing, according to mental health screeners. This study seeks to further understand how the COVID-19 pandemic has specifically impacted suicidality in adult psychiatric clients. This abstract presents on the impact of COVID-19 on clients with psychosis at risk for suicide in a community mental health setting. Methods: Quantitative and qualitative data were gathered in surveys among 6 adult clients in Washtenaw County Community Mental Health, Michigan. Findings: Participants reported that COVID-19 has made it harder to access or receive treatment (67%), their mental health has been worse (83%), and thoughts of suicide have increased (n=3, 50%). Qualitative themes related to the desire for support, transportation challenges, and service delivery changes (e.g., no virtual group therapy). Implications: Findings suggest that access to services has been a challenge due to COVID-19 and suicide prevention is a critical concern. Therefore, plans for suicide care and prevention must be examined and implemented to avoid increased suicide rates as the COVID-19 pandemic evolves.

Mental Health During COVID-19: The Effects on Suicidality Read More »

Emotion Regulation in Daily Life during COVID-19 Pandemic

The aim of this study is to assess individuals’ day-to-day emotional experiences and how they regulate their emotions, especially in context of the COVID-19 pandemic. Through conducting a 9-month longitudinal online study, we hope to identify the characteristics that are most vulnerable to COVID-19 stress and anxiety. Furthermore, we aim to examine individuals’ pattern of emotion regulation strategies to reduce COVID-19 stress and anxiety. All participants are above 18 years old, located in the University of Michigan. Recruitment was sent by a link 2,000 random University of Michigan students through the Office of Registrar. Using UM Qualtrics we first collected self-report measures of coping and emotion regulation strategies. Second, we conducted a follow-up survey using an Ecological Momentary Assessment (EMA) approach among participants who are interested in the follow-up study. During the study, EMA survey data was collected at 6 time points/per day for 5 days in spaced out intervals. The results from part 1 online-survey provide evidence that emotion regulation strategy patterns have an association with several mental health outcomes and COVID-19 related anxieties. Through these findings we acknowledge the importance of taking a person-centered approach to emotion regulation strategies especially using EMA measurement. Recently, we started another wave data collection using online-survey to understand factors that are associated with the attitude towards COVID-19 vaccinations. We hypothesized that there would be correlation between attitudes (positive/negative) towards COVID-19 and several factors across domains (cognitive, emotional, and behavioral).

Emotion Regulation in Daily Life during COVID-19 Pandemic Read More »

The Effect of Parent Education Level on Children’s Knowledge of COVID-19

Children are often told in school to wash their hands or to cover their sneezes to prevent viral transmission. Although children are more compliant with these suggestions when they understand the causal reasoning behind them, these reminders don’t include an explanation of why that action will prevent them from getting sick. Given children’s role in transmitting illness, it is important to identify effective means of educating them on how to prevent viral transmission, especially in the midst of a pandemic. Previous research on children’s understanding of germs have indicated that their knowledge is influenced by a number of factors. Given the amount of time children have spent at home over this past year, this study examines how parent education level affects the accuracy of children’s biological knowledge of COVID-19 transmission. We interviewed 180 children between the ages of 5 and 12 on their understanding of COVID-19 transmission. In particular, children were asked to identify whether a series of behaviors (e.g., singing together) could transmit COVID-19. Parents of these participants also completed a survey about their household and their experiences with COVID-19. Data analyses are ongoing. However, it is predicted that with higher levels of parental education, children will be more likely to identify behaviors that transmit COVID-19 accurately, as parents with higher levels of education may have greater understanding of the causal mechanisms behind transmission and may communicate them to their children more frequently. The results from this study will provide us insight into the extent of parental influence on children’s biological knowledge, which may, in turn, allow us to identify potential sites of intervention in schools and public health campaigns.

The Effect of Parent Education Level on Children’s Knowledge of COVID-19 Read More »

lsa logoum logo