Over the past several decades, cyberbullying has increasingly become one of the most dangerous threats to an adolescent’s mental health. Heather Springer, writing for the American Psychological Association, projects that roughly 33% of American teenagers are affected by cyberbullying while on social media (Springer). This startling percentage, compounded by an escalating need to combat cyberbullying’s negative impact on mental health, has catalyzed a wave of psychological research to explore the ways in which social media impacts teens. Over the years, researchers have produced a plethora of publications on the subject, inspiring families to pursue cyberbullying prevention for their loved ones. However, despite this surge in anti-cyberbullying interest, few researchers have attempted to coalesce these psychological findings with computer applications, and fewer still have sought to prevent cyberbullying through the strengthening of parent-teen relationships (Silva et al., 2019). Because of this, the BullyBlocker team, led by Dr. Yasin Silva and Dr. Deborah Hall, has spent the past couple years developing a mobile application called ActionPoint. Our team hopes that through this app, the risk of cyberbullying is drastically decreased and even prevented.

As Big Data becomes more relevant, existing grouping and clustering algorithms will need to be evaluated for their effectiveness with large amounts of data. Previous work in Similarity Grouping proposes a possible alternative to existing data analytics tools, which acts as a hybrid between fast grouping and insightful clustering. We, the SimCloud Team, proposed Distributed Similarity Group-by (DSG), a distributed implementation of Similarity Group By. Experimental results show that DSG is effective at generating meaningful clusters and has a lower runtime than K-Means, a commonly used clustering algorithm. This document presents my personal contributions to this team effort. The contributions include the multi-dimensional synthetic data generator, execution of the Increasing Scale Factor experiment, and presentations at the NCURIE Symposium and the SISAP 2019 Conference.

Similarity Joins are some of the most useful and powerful data processing techniques. They retrieve all the pairs of data points between different data sets that are considered similar within a certain threshold. This operation is useful in many situations, such as record linkage, data cleaning, and many other applications. While many techniques to perform Similarity Joins have been proposed, one of the most useful methods is the use of indexing structures to improve the performance of Similarity Joins. After spending pre-processing time to construct an index over a given dataset, the index structure allows for queries over that dataset to be performed significantly faster. Thus, if a dataset will have multiple Similarity Join queries performed over it, it can be beneficial to use index-based techniques to perform Similarity Join queries for that dataset. We present an extension to a previously proposed index structure, the eD-Index, which provides support for Similarity Join operators. We evaluate the performance of the algorithms and also investigate the configuration of parameters that maximizes the performance of the indexing structures. We also propose an algorithm for Multi-Way Similarity Joins using this index, which allows for Similarity Join queries between more than two data sets at a time.