Homeless Management Information System
Michael Simeone, ASU Library
ASU students working with this project learned how to interview stakeholders and refine analytics solutions over multiple iterations. This collaboration with the Knowledge Exchange for Resilience (KER) worked with local partners, Crisis Network and Valley of the Sun United Way to better understand homelessness in Maricopa County. Using data collected by the Homeless Management Information System (HMIS), our team has been working to understand patterns and variations within various groups of persons experiencing stressed and homeless circumstances, as well as prototyping predictive models that can help interventions and targeted assistance. Rapid prototyping and revision for multiple stakeholders was a key skill developed by ASU student participants.
Fake News Shelf Life
Shawn Walker, Assistant Professor of Critical Data Studies in the School of Social and Behavioral Sciences
Michael Simeone, ASU Library
Working on research about fake news helps develop skills in data acquisition, cleaning, and sampling. It also teaches responsible methodologies for understanding cultural and social trends at scale. Working with undergraduate and graduate ASU student researchers, this project aims to monitor the lifespan of hyperpartisan content that circulates on Twitter in the period leading up to national elections and democratic consultations. In past research, user-generated, hyperpartisan news content has a remarkably short shelf life, which is a marker of the perishable nature of digital content at the center of political debates in liberal democracies. Key to monitoring efforts is the storage of social media data as it is collected, such as relying on public Twitter Streaming API to track the content tweeted by users associated with key global electoral events (US 2020 Election, Brexit Referendum, etc.). The storage resources for the tweets are parsed for real-time archiving of embedded content including images and URLs embedded to the message, hence identifying and archiving the content of webpages tweeted in the context of electoral politics. From the archived data, conducting an analysis workflow will rely on topic models to contrast extant and extinct URL content tweeted in the period leading up to the vote, and during the analysis, an estimation of the size of the retweet cascade that vanished and probe the relationship between content (i.e., hyperpartisan pieces or outright fake news) and content shelf-life.
The goal is to establish metrics for the lifespan of fake news and user-generated, hyperpartisan news articles. The expectation is that the availability of this content will be short-lived and therefore hypothesize that the news cycle of hyperpartisan news deviates from the regular news cycle, including the dynamics of retweet cascades triggered by legitimate news pieces featured on Twitter.
Michael Simeone, ASU Library
Alex Kohnen, Jennifer Gorney, Clint Lord, ASU Facilities and Maintenance
Teaming with ASU Facilities and Maintenance, ASU students and Unit for Data Science faculty and staff conducted beneficiary discovery, basic research, and analyzed thousands of facilities and maintenance requests submitted at Arizona State University over 5 years. These reports provided a unique view into the operations of the ASU campus, as well as the reliability and performance of green infrastructure at ASU. The final product is a prototype prediction system for breakdowns and recurrent problems, to be site tested with ASU facilities using live data. This project was funded by the Office for Naval Research and emphasizes student expertise, development of science and technology leadership skills, and student veteran engagement.
Hi! I am Shefali Anand, studying MS in Software Engineering at ASU. My journey in Data Science and Analytics Lab at ASU’s Hayden Library has been quite amazing. I joined the lab in Spring 2019 and since then my knowledge in Data Science has improved exponentially. It started in Fall 2018, my friend referred me to Michael Simeone, our Director. I explained my work in the Machine Learning projects which I did during my term, as a Software Engineer at Samsung. Fortunately, in Spring 2019, I was offered a Research Assistantship in the Data Science lab..
I began working on Neptune’s Classification project with two other teammates. The project was about classifying Human Errors in the Instruction Reports of US’s Nuclear Power Plants. Yes, Nuclear Power Plants. I then realized that my work could save thousands of human lives. This project gave me the scope to learn Natural Language Processing (NLP) which was quite new to me. I have explored and learned a lot about NLP and various algorithms including Word2Vec, CNN, LSTM, and BERT; and have tweaked them to achieve better accuracy. Implementing Machine Learning algorithms on a trained data is easy, but what if there’s no training data and you could imagine that doing Unsupervised Learning on huge documents is not an easy task. So, here at Data Science Lab we learn, research, experiment, and implement solutions of common and not so common problems. This is what makes me feel passionate about my job!
I started out with little prior industry experience. The Unit for Data Science and Analytics gave me an opportunity to collaborate with people and understand the dynamics of the current projects. Later, I was a part of the Neptune project, wherein I developed a web application, the OrgBrowser. This web application helps analyse organizational document records. It is built around three different routines, with complex natural language processing algorithms running in the backend. This helped me augment my experience with web technologies, such as nginx, and flask. I’ve also had the opportunity work on a project to mine the UberCrash tweets. My primary objective was to draw out people’s opinions on the incident and whether or not it affected how people think about self-driving cars in general. This exposed me to a variety of practices in NLP. My current work involves designing a decision support system built on top of the Homeless Management Information Systems dataset. We are working in conjunction with the Decision Theatre, to build complex multi-screen analytical web applications using Shiny-R. As a graduate student in computer science, these projects fostered my growth and helped me align my career goals.
The Data Science Lab is a place where your enthusiasm doesn’t go unnoticed. People embrace your ideas and help improve upon them collaboratively. Through regular unit meetings and interactions, different ideas are brought to the table, giving you an opportunity to dive into other interesting projects. Above all, this is a place where actual problem solving happens, and I am more than grateful to be a part of this team.
My employment at the Data Science Lab began through an opportunity for student veterans. Not only have I learned invaluable computational skills, but the experience has also given me an entirely new perspective on how to approach research design. Through working on project NEPTUNE, I became well-versed in natural language processing and social network analysis techniques. In addition, the interdisciplinary nature of the lab empowered those from the social sciences to make improvements on existing conceptual models. Specifically, my work entailed extracting employee operational networks and relating those findings to safety performance. As an incoming doctoral student of anthropology, this newfound passion for facilitating enhanced cooperation between social and data scientists will follow me for the rest of my academic career. I believe that if diverse thinkers embrace big data analytics, academics can enhance real world problem-solving efforts.
Kuldeep Singh Rathor
I remember during Summer of 2018 when I was looking for some cool projects to work on and I stumbled upon the Data Science lab's website through the ASU portal. I immediately sent email to the Director, Michael Simeone regarding the cool projects I saw on the website. I began working on a cool task of Moon Crater Classification as a volunteer. This boosted up my confidence regarding Machine Learning and Data Science. Fortunately, there was a research aide position opening and I applied. I got the position after an amazing interview. Fast forward to now, I have worked on multiple projects like the Moon Crater Classification, Visualization for error flow in Nuclear Power Plants' roles, and Document classification for Department of Naval Defense. Dr. Simeone and the Data Science Lab has helped me hone my skills in Data Science and Machine Learning in such a way that I can implement solutions for real problems now. It has been great working here with such supportive lab members.
Deepan Karthik Nedumaran
I gained the opportunity to work in the Data Science and Analytics Lab in my first semester and since then it's been a great journey of learning and interaction. Professor Michael Simeone and team provided a platform for creative work and progressive learning.
I was allowed to work on a variety projects to expand my horizons in the data field. The most interesting project involved predictive maintenance of appliances in a large organization. My objective was to design a model to analyze the maintenance requests and predict the issues beforehand. This was a challenging project, because I had to consider various external parameters and all issues were to be dealt based on the season. We used a time series model called the SARIMAX and built a dashboard to show the expected number of tickets in the near future. In addition to the prediction model, we also categorized the issues using the comments in each ticket with an unsupervised learning technique called the topic modelling. The project was well received and we got a chance to present it to the Department of Defense. This model can be used to perform preventive maintenance tasks and determine end of life for instruments.
I was also given a chance to work on multiple other projects where I explored cutting edge technologies and experiment with new techniques. Working on these projects motivated me to take related courses and learn more about data modelling, analysis, and visualization. Therefore, working on various projects and developing applications in the Data Science lab helped me secure multiple job opportunities in the industry.
As a data scientist, I love working with data of all kinds. While data might be ubiquitous today, not all of it is useful and it can be challenging to find relevant information in this huge haystack. Working at the Unit for Data Science has given me an opportunity to solve real-world problems that require me to extract meaningful insights from data. Having worked on multiple projects at the lab, I have gotten to delve into various domains in the data science realm such as Natural Language Processing, Time Series Analysis, Machine Learning and Data Visualization. The diverse set of problems undertaken at the lab enables us students to interact with stakeholders from different backgrounds and areas of work. Getting such hands-on experience in an ever-growing field such as data science is immensely useful for those looking to pursue a career in this field. As a Computer Science graduate student looking to venture into Data Science, the mentorship that I have received from Dr. Michael Simeone has been invaluable. This lab has served as a platform for me to learn, grow and collaborate with astute colleagues and peers in a professional setting. In addition to the classes in my master’s course, the practical learning experience that I have gained from the lab has been incredible.
Who we're working with
- Institute for Humanities Research
- Ira A. Fulton School of Engineering
- School for the Future of Innovation in Society
- School of Computing, Informatics and Decision Systems Engineering
- School of Historical, Philosophical and Religious Studies
- School of International Letters and Cultures
- School of Sustainability