Prejudice and hate directed toward Asian individuals has increased in prevalence and salience during the COVID-19 pandemic, with notable rises in physical violence. Concurrently, as many governments enacted stay-at-home mandates, the spread of anti-Asian content increased in online spaces, including social media. In the present study, we investigated temporal and geographical patterns in social media content relevant to anti-Asian prejudice during the COVID-19 pandemic. Using the Twitter Data Collection API, we queried over 13 million tweets posted between January 30, 2020, and April 30, 2021, for both negative (e.g., #kungflu) and positive (e.g., #stopAAPIhate) hashtags and keywords related to anti-Asian prejudice. In a series of descriptive analyses, we found differences in the frequency of negative and positive keywords based on geographic location. Using burst detection, we also identified distinct increases in negative and positive content in relation to key political tweets and events. These largely exploratory analyses shed light on the role of social media in the expression and proliferation of prejudice as well as positive responses online.

Increased social media use has contributed to the greater prevalence of abusive, rude, and offensive textual comments. Machine learning models have been developed to detect toxic comments online, yet these models tend to show biases against users with marginalized or minority identities (e.g., females and African Americans). Established research in debiasing toxicity classifiers often (1) takes a static or batch approach, assuming that all information is available and then making a one-time decision; and (2) uses a generic strategy to mitigate different biases (e.g., gender and racial biases) that assumes the biases are independent of one another. However, in real scenarios, the input typically arrives as a sequence of comments/words over time instead of all at once. Thus, decisions based on partial information must be made while additional input is arriving. Moreover, social bias is complex by nature. Each type of bias is defined within its unique context, which, consistent with intersectionality theory within the social sciences, might be correlated with the contexts of other forms of bias. In this work, we consider debiasing toxicity detection as a sequential decision-making process where different biases can be interdependent. In particular, we study debiasing toxicity detection with two aims: (1) to examine whether different biases tend to correlate with each other; and (2) to investigate how to jointly mitigate these correlated biases in an interactive manner to minimize the total amount of bias. At the core of our approach is a framework built upon theories of sequential Markov Decision Processes that seeks to maximize the prediction accuracy and minimize the bias measures tailored to individual biases. Evaluations on two benchmark datasets empirically validate the hypothesis that biases tend to be correlated and corroborate the effectiveness of the proposed sequential debiasing strategy.

Social media is a vital means for information-sharing due to its easy access, low cost, and fast dissemination characteristics. However, increases in social media usage have corresponded with a rise in the prevalence of cyberbullying. Most existing cyberbullying detection methods aresupervised and, thus, have two key drawbacks: (1) The data labeling process is often time-consuming and labor-intensive; (2) Current labeling guidelines may not be generalized to future instances because of different language usage and evolving social networks. To address these limitations, this work introduces a principled approach forunsupervised cyberbullying detection. The proposed model consists of two main components: (1) Arepresentation learning network that encodes the social media session by exploiting multi-modal features, e.g., text, network, and time. (2) Amulti-task learning network that simultaneously fits the comment inter-arrival times and estimates the bullying likelihood based on a Gaussian Mixture Model. The proposed model jointly optimizes the parameters of both components to overcome the shortcomings of decoupled training. Our core contribution is an unsupervised cyberbullying detection model that not only experimentally outperforms the state-of-the-art unsupervised models, but also achieves competitive performance compared to supervised models.

Cyberbullying has become one of the most pressing online risks for young people and has raised serious concerns in society. The emerging literature identifies cyberbullying as repetitive acts that occur over time rather than one-off incidents. Yet, there has been relatively little work to model the hierarchical structure of social media sessions and the temporal dynamics of cyberbullying in online social network sessions. We propose a hierarchical attention network for cyberbullying detection that takes these aspects of cyberbullying into account. The primary distinctive characteristics of our approach include: (i) a hierarchical structure that mirrors the structure of a social media session; (ii) levels of attention mechanisms applied at the word and comment level, thereby enabling the model to pay different amounts of attention to words and comments, depending on the context; and (iii) a cyberbullying detection task that also predicts the interval of time between two adjacent comments. These characteristics allow the model to exploit the commonalities and differences across these two tasks to improve the performance of cyberbullying detection. Experiments on a real-world dataset from Instagram, the social media platform on which the highest percentage of users have reported experiencing cyberbullying, reveal that the proposed architecture outperforms the state-of-the-art method.

Over the last decade, research has revealed the high prevalence of cyberbullying among youth and raised serious concerns in society. Information on the social media platforms where cyberbullying is most prevalent (e.g., Instagram, Facebook, Twitter) is inherently multi-modal, yet most existing work on cyberbullying identification has focused solely on building generic classification models that rely exclusively on text analysis of online social media sessions (e.g., posts). Despite their empirical success, these efforts ignore the multi-modal information manifested in social media data (e.g., image, video, user profile, time, and location), and thus fail to offer a comprehensive understanding of cyberbullying. Conventionally, when information from different modalities is presented together, it often reveals complementary insights about the application domain and facilitates better learning performance. In this paper, we study the novel problem of cyberbullying detection within a multi-modal context by exploiting social media data in a collaborative way. This task, however, is challenging due to the complex combination of both cross-modal correlations among various modalities and structural dependencies between different social media sessions, and the diverse attribute information of different modalities. To address these challenges, we propose XBully, a novel cyberbullying detection framework, that first reformulates multi-modal social media data as a heterogeneous network and then aims to learn node embedding representations upon it. Extensive experimental evaluations on real-world multi-modal social media datasets show that the XBully framework is superior to the state-of-the-art cyberbullying detection models.

Set similarity join is an essential operation in big data analytics, e.g., data integration and data cleaning, that finds similar pairs from two collections of sets. To cope with the increasing scale of the data, distributed algorithms are called for to support large-scale set similarity joins. Multiple techniques have been proposed to perform similarity joins using MapReduce in recent years. These techniques, however, usually produce huge amounts of duplicates in order to perform parallel processing successfully as MapReduce is a shared-nothing framework. The large number of duplicates incurs on both large shuffle cost and unnecessary computation cost, which significantly decrease the performance. Moreover, these approaches do not provide a load balancing guarantee, which results in a skewness problem and negatively affects the scalability properties of these techniques. To address these problems, in this paper, we propose a duplicatefree framework, called FS-Join, to perform set similarity joins efficiently by utilizing an innovative vertical partitioning technique. FS-Join employs three powerful filtering methods to prune dissimilar string pairs without computing their similarity scores. To further improve the performance and scalability, FS-Join integrates horizontal partitioning. Experimental results on three real datasets show that FS-Join outperforms the state-of-theart methods by one order of magnitude on average, which demonstrates the good scalability and performance qualities of the proposed technique.

Cyberbullying is the most common online risk for adolescents, and it has been reported that over half of young people do not tell their parents when it occurs. Cyberbullying involves the deliberate use of online digital media to communicate false or embarrassing information about another person. While previous work has extensively analyzed the nature and prevalence of cyberbullying, there has been significantly less work in the area of automated identification of cyberbullying, particularly in social networking sites. The focus of our work is to develop a computational model to identify and measure the intensity of cyberbullying in social networking sites. In this paper, we present and demonstrate BullyBlocker, an app that identifies instances of cyberbullying in Facebook and notifies parents when it occurs. This paper presents the most relevant characteristics of our initial cyberbullying identification model, key app design and implementation details, the demonstration scenarios, and several areas of future work to improve upon the initial model.

Cyberbullying is the deliberate use of online digital media to communicate false, embarrassing, or hostile information about another person. It is the most common online risk for adolescents and well over half of young people do not tell their parents when it occurs. While there have been many studies about the nature and prevalence of cyberbullying, there has been relatively less work in the area of automated identification of cyberbullying in social media sites. The focus of our work is to develop an automated model to identify and measure the degree of cyberbullying in social networking sites, and a Facebook app for parents, built on this model, that notifies them when cyberbullying occurs. This paper describes the challenges associated with building a computer model for cyberbullying identification, presents key results from psychology research that can be used in such a model, describes an initial model and mobile app design for cyberbullying identification, and describes key areas of future work to improve upon the initial model.

The SQL group-by operator plays an important role in summarizing and aggregating large datasets in a data analytics stack. The Similarity SQL-based Group-By operator (SGB, for short) extends the semantics of the standard SQL Group-by by grouping data with similar but not necessarily equal values. While existing similarity-based grouping operators efficiently realize these approximate semantics, they primarily focus on one-dimensional attributes and treat multi-dimensional attributes independently. However, correlated attributes, such as in spatial data, are processed independently, and hence, groups in the multi-dimensional space are not detected properly. To address this problem, we introduce two new SGB operators for multi-dimensional data. The first operator is the clique (or distance-to-all) SGB, where all the tuples in a group are within some distance from each other. The second operator is the distance-to-any SGB, where a tuple belongs to a group if the tuple is within some distance from any other tuple in the group. Since a tuple may satisfy the membership criterion of multiple groups, we introduce three different semantics to deal with such a case: (i) eliminate the tuple, (ii) put the tuple in any one group, and (iii) create a new group for this tuple. We implement and test the new SGB operators and their algorithms inside PostgreSQL. The overhead introduced by these operators proves to be minimal and the execution times are comparable to those of the standard Group-by. The experimental study, based on TPC-H and a social check-in data, demonstrates that the proposed algorithms can achieve up to three orders of magnitude enhancement in performance over baseline methods developed to solve the same problem.

The SQL group-by operator plays an important role in summarizing and aggregating large datasets in a data analytics stack. While the standard group-by operator, which is based on equality, is useful in several applications, allowing similarity aware grouping provides a more realistic view on real-world data that could lead to better insights. The Similarity SQL-based Group-By operator (SGB, for short) extends the semantics of the standard SQL Group-by by grouping data with similar but not necessarily equal values. While existing similarity-based grouping operators efficiently realize these approximate semantics, they primarily focus on one-dimensional attributes and treat multi-dimensional attributes independently. However, correlated attributes, such as in spatial data, are processed independently, and hence, groups in the multi-dimensional space are not detected properly. To address this problem, we introduce two new SGB operators for multi-dimensional data. The first operator is the clique (or distance-to-all) SGB, where all the tuples in a group are within some distance from each other. The second operator is the distance-to-any SGB, where a tuple belongs to a group if the tuple is within some distance from any other tuple in the group. Since a tuple may satisfy the membership criterion of multiple groups, we introduce three different semantics to deal with such a case: (i) eliminate the tuple, (ii) put the tuple in any one group, and (iii) create a new group for this tuple. We implement and test the new SGB operators and their algorithms inside PostgreSQL. The overhead introduced by these operators proves to be minimal and the execution times are comparable to those of the standard Group-by. The experimental study, based on TPC-H and a social check-in data, demonstrates that the proposed algorithms can achieve up to three orders of magnitude enhancement in performance over baseline methods developed to solve the same problem.

A key area of focus in recent Computer Science education research has been block-based programming. In this approach, program instructions are represented as visual blocks with shapes that control the way multiple instructions can be combined. Since programs are created by dragging and connecting blocks, the focus is on the program's logic rather than its syntax. In this demonstration we present DBSnap, a system that enables building database queries, specifically relational algebra queries, by connecting blocks. A differentiating property of DBSnap is that it uses a visual tree-based structure to represent queries. This structure is, in fact, very similar to the intuitive query trees commonly used by database practitioners and educators. DBSnap is also highly dynamic, it shows the query result and the corresponding relational algebra expression as the query is built and enables the inspection of intermediate query results. This paper describes DBSnap's main design elements, its architecture and implementation guidelines, and the interactive demonstration scenarios. DBSnap is a publicly available system and aims to have a transformational effect on database learning.

Many companies now routinely run massive data analysis jobs -- expressed in some scripting language -- on large clusters of low-end servers. Many analysis scripts are complex and contain common sub expressions, that is, intermediate results that are subsequently joined and aggregated in multiple different ways. Applying conventional optimization techniques to such scripts will produce plans that execute a common sub expression multiple times, once for each consumer, which is clearly wasteful. Moreover, different consumers may have different physical requirements on the result: one consumer may want it partitioned on a column A and another one partitioned on column B. To find a truly optimal plan, the optimizer must trade off such conflicting requirements in a cost-based manner. In this paper we show how to extend a Cascade-style optimizer to correctly optimize scripts containing common sub expression. The approach has been prototyped in SCOPE, Microsoft's system for massive data analysis. Experimental analysis of both simple and large real-world scripts shows that the extended optimizer produces plans with 21 to 57% lower estimated costs.

Cloud enabled systems have become a crucial component to efficiently process and analyze massive amounts of data. One of the key data processing and analysis operations is the Similarity Join, which retrieves all data pairs whose distances are smaller than a pre-defined threshold ∈. Even though multiple algorithms and implementation techniques have been proposed for Similarity Joins, very little work has addressed the study of Similarity Joins for cloud systems. This paper presents MRSimJoin, a multi-round MapReduce based algorithm to efficiently solve the Similarity Join problem. MRSimJoin efficiently partitions and distributes the data until the subsets are small enough to be processed in a single node. The proposed algorithm is general enough to be used with data that lies in any metric space. We have implemented MRSimJoin in Hadoop, a highly used open-source cloud system. We show how this operation can be used in multiple real-world data analysis scenarios with multiple data types and distance functions. Particularly, we show the use of MRSimJoin to identify similar images represented as feature vectors, and similar publications in a bibliographic database. We also show how MRSimJoin scales in each scenario when important parameters, e.g., ∈, data size and number of cluster nodes, increase. We demonstrate the execution of MRSimJoin queries using an Amazon Elastic Compute Cloud (EC2) cluster.

Similarity Joins are recognized among the most useful data processing and analysis operations and are extensively used in multiple application domains. They retrieve all data pairs whose distances are smaller than a predefined threshold ε. Multiple Similarity Join algorithms and implementation techniques have been proposed. They range from out-of-database approaches for only in-memory and external memory data to techniques that make use of standard database operators to answer similarity joins. Recent work has shown that this operation can be efficiently implemented as a physical database operator. However, the proposed operator only support 1D numeric data. This paper presents DBSimJoin , a physical Similarity Join database operator for datasets that lie in any metric space. DBSimJoin is a non-blocking operator that prioritizes the early generation of results. We implemented the proposed operator in PostgreSQL, an open source database system. We show how this operator can be used in multiple real-world data analysis scenarios with multiple data types and distance functions. Particularly, we show the use of DBSimJoin to identify similar images represented as feature vectors, and similar publications in a bibliographic database. We also show that DBSimJoin scales very well when important parameters, e.g., e, data size, increase.

The cycle of processing the data in many application domains is complex and may involve real-world activities that are external to the database, e.g., wet-lab experiments, instrument readings, and manual measurements. These real-world activities may take long time to prepare for and to perform, and hence introduce inherently long time delays between the updates in the database. The presence of these long delays between the updates, along with the need for the intermediate results to be instantly available, makes supporting real-world activities in the database engine a challenging task. In this paper, we address these challenges through a system that enables users to reflect their updates immediately into the database while keeping track of the dependent and potentially invalid data items until they are re-validated. The proposed system includes: (1) semantics and syntax for interfaces through which users can express the dependencies among data items, (2) new operators to alert users when the returned query results contain potentially invalid or out-of-date data, and to enable evaluating queries on either valid data only, or both valid and potentially invalid data, and (3) mechanisms for data invalidation and revalidation. The proposed system is being realized via extensions to PostgreSQL.

Similarity joins have been studied as key operations in multiple application domains, e.g., record linkage, data cleaning, multimedia and video applications, and phenomena detection on sensor networks. Multiple similarity join algorithms and implementation techniques have been proposed. They range from out-of-database approaches for only in-memory and external memory data to techniques that make use of standard database operators to answer similarity joins. Unfortunately, there has not been much study on the role and implementation of similarity joins as database physical operators. In this paper, we focus on the study of similarity joins as first-class database operators. We present the definition of several similarity join operators and study the way they interact among themselves, with other standard database operators, and with other previously proposed similarity-aware operators. In particular, we present multiple transformation rules that enable similarity query optimization through the generation of equivalent similarity query execution plans. We then describe an efficient implementation of two similarity join operators, ¿-Join and Join-Around, as core DBMS operators. The performance evaluation of the implemented operators in PostgreSQL shows that they have good execution time and scalability properties. The execution time of Join-Around is less than 5% of the one of the equivalent query that uses only regular operators while ¿-Join's execution time is 20 to 90% of the one of its equivalent regular operators based query for the useful case of small ¿ (0.01% to 10% of the domain range). We also show experimentally that the proposed transformation rules can generate plans with execution times that are only 10% to 70% of the ones of the initial query plans.

The identification and processing of similarities in the data play a key role in multiple application scenarios. Several types of similarity-aware operations have been studied in the literature. However, in most of the previous work, similarity-aware operations are studied in isolation from other regular or similarity-aware operations. Furthermore, most of the previous research in the area considers a standalone implementation, i.e., without any integration with a database system. In this demonstration we present SimDB, a similarity-aware database management system. SimDB supports multiple similarity-aware operations as first-class database operators. We describe the architectural changes to implement the similarity-aware operators. In particular, we present the way conventional operators' implementation machinery is extended to support similarity-aware operators. We also show how these operators interact with other similarity-aware and regular operators. In particular, we show the effectiveness of multiple equivalence rules that can be used to extend cost-based query optimization to the case of similarity-ware operations.

Annotations play a key role in understanding and curating databases. Annotations may represent comments, descriptions, lineage information, among several others. Annotation management is a vital mechanism for sharing knowledge and building an interactive and collaborative environment among database users and scientists. What makes it challenging is that annotations can be attached to database entities at various granularities, e.g., at the table, tuple, column, cell levels, or more generally, to any subset of cells that results from a select statement. Therefore, simple comment fields in tuples would not work because of the combinatorial nature of the annotations. In this paper, we present extensions to current database management systems to support annotations. We propose storage schemes to efficiently store annotations at multiple granularities, i.e., at the table, tuple, column, and cell levels. Compared to storing the annotations with the individual cells, the proposed schemes achieve more than an order-of-magnitude reduction in storage and up to 70% saving in the query execution time. We define types of annotations that inherit different behaviors. Through these types, users can specify, for example, whether or not an annotation is continuously applied over newly inserted data and whether or not an annotation is archived when the base data is modified. These annotation types raise several storage and processing challenges that are addressed in the paper. We propose declarative ways to add, archive, query, and propagate annotations. The proposed mechanisms are realized through extensions to the standard SQL. We implemented the proposed functionalities inside PostgreSQL with an easy to use Excel-based front-end graphical interface.

Decision Support Systems (DSS) are information systems that support decision making processes. In many scenarios these systems are built on top of data managed by DBMSs and make extensive use of its underlying grouping and aggregation capabilities, i.e., Group-by operation. Unfortunately, the standard grouping operator has the inherent limitation of being based only on equality, i.e., all the tuples in a group share the same values of the grouping attributes. Similarity-based Group-by (SGB) has been recently proposed as an extension aimed to overcome this limitation. SGB allows fast formation of groups with similar objects under different grouping strategies and the pipelining of results for further processing. This demonstration presents how SGB can be effectively used to build useful DSSs. The presented DSS has been built around the data model and queries of the TPC-H benchmark intending to be representative of complex business analysis applications. The system provides intuitive dashboards that exploit similarity aggregation queries to analyze: (1) customer clustering, (2) profit and revenue, (3) marketing campaigns, and (4) discounts. The presented DSS runs on top of PostgreSQL whose query engine is extended with similarity grouping operators.

Privacy preservation has become an important requirement in information systems that deal with personal data. In many cases this requirement is imposed by laws that recognize the right of data owners to control whom their information is shared with and the purposes for which it can be shared. Hippocratic databases have been proposed as an answer to this privacy requirement; they extend the architecture of standard DBMSs with components that ensure personal data is handled in compliance with its associated privacy definitions. Previous work in Hippocratic databases has proposed the design of some of these components. Unfortunately, there has not been much work done to implement these components as an integral part of a DBMS and study the problems faced to realize the Hippocratic databases. The main goal of the 'Hippocratic PostgreSQL' project is to perform this implementation and study. The project includes the implementation of components to support limited disclosure, limited retention time, and management of multiple policies and policy versions. This demo presents the use of these components both from a terminal-based SQL command interface and through a Web-based healthcare application that makes use of the implemented database-level privacy features. Hippocratic PostgreSQL has the novel feature of augmenting both k-anonymity and generalization hierarchies into the Hippocratic DBMS engine functionality. Several interesting problems emerge as a result and their solutions are presented in the context of this demo.

Group-by is a core database operation that is used extensively in OLTP, OLAP, and decision support systems. In many application scenarios, it is required to group similar but not necessarily equal values. In this paper we propose a new SQL construct that supports similarity-based group-by (SGB). SGB is not a new clustering algorithm, but rather is a practical and fast similarity grouping query operator that is compatible with other SQL operators and can be combined with them to answer similarity-based queries efficiently. In contrast to expensive clustering algorithms, the proposed similarity group-by operator maintains low execution times while still generating meaningful groupings that address many application needs. The paper presents a general definition of the similarity group-by operation and gives three instances of this definition. The paper also discusses how optimization techniques for the regular group-by can be extended to the case of SGB. The proposed operators are implemented inside PostgreSQL. The performance study shows that the proposed similarity-based group-by operators have good scalability properties with at most only 25% increase in execution time over the regular group-by.

We demonstrate bdbms, an extensible database engine for biological databases, bdbms started on the observation that database technology has not kept pace with the specific requirements of biological databases and that several needed key functionalities are not supported at the engine level. While bdbms aims at supporting several of these functionalities, this demo focuses on: (1) Annotation and provenance management including storage, indexing, querying, and propagation, (2) Local dependency tracking of dependencies and derivations among data items, and (3) Update authorization to support data curation. We demonstrate how bdbms enables biologists to manipulate their databases, annotations, and derivation information in a unified database system using the Purdue ionomics information management system (PiiMS) as a case study.