Meet the Team
Gabriella Vozar
Hi my name is Gabriella, I go by Gabi. I am one of the DIGIT majors here at Penn State Behrend. I hail from the Pittsburgh area and began my college career at Penn State New Kensington where I served as a Student Athlete before transferring north.
I led the web design, architecting the HTML structure and optimizing CSS to create a cohesive, visually engaging, and user‑friendly interface that seamlessly showcased my teammates’ contributions.
Dannika Love
Hi all! My name is Dannika Love and I am a DIGIT student at Penn State Behrend! I am the daughter of Jodie and Ron, I have an older sister, Kalie, along with a brother-in-law, Dan. I enjoy being creative, along with cooking and bakeing. I also just like having time to relax on my phone. I am a really big family person, I love my family so much, I currently live two hours from home to go to college and it is not the easiest thing to do. I enjoy hanging out with my family and my boyfriend, Gavin, along with his family. I love going to see my grandma, who is an absolute hoot.
As team lead, I contributed extensively to data processing, analysis, and web development. I began by uploading the episode transcripts as individual text files. I developed multiple web pages, including one displaying the original XML, XSLT, and output files, and another featuring a breakdown of the show’s main characters along with an SVG-based character connection visualization. Using AntConc, I identified two sets of groups—keywords and character names—and created two corresponding kumu.io visualizations. I also generated an SVG frequency graph for both groups to enhance the project’s visuals. Additionally, I wrote a Python script that processed XSLT-filtered dialogue files to produce a TSV file, which was then used to create a Cytoscape network visualization. I manually went through each processed xml file to add additional attributes that were missed by the xslt that I thought would add more and then made a relaxNG file and associated it with xml files. I added a Creative Commons license to the project and linked all sources referenced during our research. Throughout the project, I delegated tasks to team members and managed pull requests to keep our GitHub repository organized and up to date.
Emily Kalie
Hello fellow Digit lovers, my name is Emily Kalie and I am 23 years old. I will be graduating this coming December. I love to spend time with my family and close friends. My family has two Golden Retrievers, Murphy and Maple. They are a bit crazy and sometimes a handful but bring the most love to everyone who meets them. I am a huge Pittsburgh Penguins fan and love to watch all of their games. I also enjoy the time I get to spend volunteering at the Emmaus Soup kitchen each month with my mom. I have a strong love for technology with a passion for adapting to & learning new technology.
This project team worked well together. My main contributions to this project was a lot of Jupyter Notebook work, that dealt with our episodes text files and turning them into TSV documents or just regular data output to then incorporate into our project. The TSV’s that I made mostly worked but the one that I made with all of the episodes finding verbs, names, and proper nouns, was able to be brought into CytoScape. But when it came time to adding my Cyto to our html page I tried everything and still could not get the Cyto to work in an interactive way on our page. I also made the About page on the site that states different information about the show, cast, and plot. I created an SVG’s that we used as a part of our visualizations, this SVG was comparing the top 25 verbs throught the epiodes formated in a bar chart.
Raashee Mishra
Hey! My name is Raashee and I am from New Jersey and am a 20 year old college student. I am currently in my third year of studying in the DIGIT program at the Pennsylvania State University. I have a passion for publication design, web developing, and graphic design. Alongside, I enjoy following fashion and reading any and all science fiction!
My contributions to this project range over several responsibilities. In order to transform the raw text files of the "Cold Case" transcripts to clean, source text files our team could work with, I developed an XSLT that applied XML markup to all 23 text files. Integrated within this XSLT was Regex, this facilitated the markup process to tackle the several inconsistencies within the transcripts, to lay a solid foundation for the next phase of our project, text analysis! After establishing our research goals for our text analysis, more XSLTs were developed (with the help of Dr.B) to assist us with this process. Using the outputs of an XSLT that created text files consisting of any music within the episodes, I based my text analysis on finding patterns of theme within the word frequency of the music lyrics within these text files in hopes they correlate to the theme of it's respective episode. To do this, I used Jupyter Notebook to create an SVG of a bar graph that displayed the most frequently used verbs in all of the music text files. Then, to develop a means of text analysis with more intricacy, I used Jupyter Notebook to produce TSV files to input within Cytoscape. This outputted a network that displays the most frequently mentioned verbs within each episode. In order to display these developments, I created a soundtrack page on our website that provides context for users to understand my research goals. Additionally, I worked with Emily to make our Cytoscape page fully interactive with additional descriptive elements. To do this, I used Jupyter Notebook to output Java Script files to embed within the HTML file for this Cytoscape webpage.