Steven R Wilson

Oakland University · Department of Computer Science and Engineering

People's values provide a decision-making framework that helps guide their everyday actions. Most popular methods of assessing values show tenuous relationships with everyday behaviors. Using a new Amazon Mechanical Turk dataset (N = 767) consisting of people's language, values, and behaviors , we explore the degree to which attaining " ground trut...

We present a methodology based on topic modeling that can be used to identify and quantify sociolinguistic differences between groups of people, and describe a regression method that can disentangle the influences of different attributes of the people in the group (e.g., culture, gender, age). As an example, we explore the concept of personal value...

The things people do in their daily lives can provide valuable insights into their personality, values, and interests. Unstruc-tured text data on social media platforms are rich in behavioral content, and automated systems can be deployed to learn about human activity on a broad scale if these systems are able to reason about the content of interes...

Crossword puzzles are popular word games that require not only a large vocabulary, but also a broad knowledge of topics. Answering each clue is a natural language task on its own as many clues contain nuances, puns, or counter-intuitive word definitions. Additionally, it can be extremely difficult to ascertain definitive answers without the constra...

Background: The existence of toxic conversations in open-source platforms can degrade relationships among software developers and may negatively impact software product quality. To help mitigate this, some initial work has been done to detect toxic comments in the Software Engineering (SE) domain. Aims: Since automatically classifying an entire tex...

COVID-19 poses disproportionate mental health consequences to the public during different phases of the pandemic. We use a computational approach to capture the specific aspects that trigger the public's anxiety about the pandemic and investigate how these aspects change over time. First, we identified nine subjects of anxiety (SOAs) in a sample of...

Systematic Offensive stereotyping (SOS) in word embeddings could lead to associating marginalised groups with hate speech and pro-fanity, which might lead to blocking and silencing those groups, especially on social media platforms. In this work, we introduce a quantitative measure of the SOS bias, validate it in the most commonly used word embeddi...

Computational humor detection systems rarely model the subjectivity of humor responses, or consider alternative reactions to humor - namely offense. We analyzed a large dataset of humor and offense ratings by male and female annotators of different age groups. We find that women link these two concepts more strongly than men, and they tend to give...

COVID-19 poses disproportionate mental health consequences to the public during different phases of the pandemic. We use a computational approach to capture the specific aspects that trigger an online community's anxiety about the pandemic and investigate how these aspects change over time. First, we identified nine subjects of anxiety (SOAs) in a...

Computational humor detection systems rarely model the subjectivity of humor responses, or consider alternative reactions to humor - namely offense. We analyzed a large dataset of humor and offense ratings by male and female annotators of different age groups. We find that women link these two concepts more strongly than men, and they tend to give...

iSarcasmEval is the first shared task to target intended sarcasm detection: the data for this task was provided and labelled by the authors of the texts themselves. Such an approach min-imises the downfalls of other methods to collect sarcasm data, which rely on distant supervision or third-party annotations. The shared task contains two languages,...

Narratives have been shown to be an effective way to communicate health risks and promote health behavior change, and given the growing amount of health information being shared on social media, it is crucial to study health- related narratives in social media. However, expert identification of a large number of narrative texts is a time consuming...

As an online, crowd-sourced, open English-language slang dictionary, the Urban Dictionary platform contains a wealth of opinions, jokes, and definitions of terms, phrases, acronyms, and more. However, it is unclear exactly how activity on this platform relates to larger conversations happening elsewhere on the web, such as discussions on larger, mo...

The choice of the corpus on which word embeddings are trained can have a sizable effect on the learned representations, the types of analyses that can be performed with them, and their utility as features for machine learning models. To contribute to the existing sets of pre-trained word embeddings, we introduce and release the first set of word em...

There are several standard methods used to measure personal values, including the Schwartz Values Survey and the World Values Survey. While these tools are based on well-established questionnaires, they are expensive to administer at a large scale and rely on respondents to self-report their values rather than observing what people actually choose...

The original version of this chapter was revised. A missing citation was added and the bibliography was updated accordingly.

Events and situations unfold quickly in our modern world, generating streams of Internet articles, photos, and videos. The ability to automatically sort through this wealth of information would allow us to identify which pieces of information are most important and credible, and how trends unfold over time. In this paper, we present the first piece...

The activities we do are linked to our interests, personality, political preferences, and decisions we make about the future. In this paper, we explore the task of predicting human activities from user-generated content. We collect a dataset containing instances of social media users writing about a range of everyday activities. We then use a state...

Understanding current world events in real-time involves sifting through news articles, tweets, photos, and videos from many different perspectives. The goal of the DARPA-funded AIDA project is to automate much of this process, building a knowledge base that can be queried to strategically generate hypotheses about different aspects of an event. We...

We introduce a crowd-powered approach for the creation of a lexicon for any theme given a set of seed words that cover a variety of concepts within the theme. Terms are initially sorted by automatically clustering their embeddings and subsequently rearranged by crowd workers in order to create a tree structure. This type of organization captures hi...

Previous work has investigated the identification of mental health issues in social media users, yet the way that users’ mental states and related behavior change over time remains relatively understudied. This paper focuses on online mental health communities and studies how users’ contributions to these communities change over one year. We define...

The semantic relations between two short texts can be defined in multiple ways. Yet, all the systems to date designed to capture such relations target one relation at a time. We propose a novel multi-label transfer learning approach to jointly learn the information provided by the multiple annotations, rather than treating them as separate tasks. N...

We study the problem of adapting neural sentence embedding models to the domain of human activities to capture their relations in different dimensions. We introduce a novel approach, Sequential Network Transfer, and show that it largely improves the performance on all dimensions. We also extend this approach to other semantic similarity datasets, a...

People's personality and motivations are manifest in their everyday language usage. With the emergence of social media, ample examples of such usage are procurable. In this paper, we aim to analyze the vocabulary used by close to 200,000 Blogger users in the U.S. with the purpose of geographically portraying various demographic, linguistic, and psy...

Texts posted on the web by users from diverse cultures provide a nearly endless source of data that researchers can use to study human thoughts and language patterns. However, unless care is taken to avoid it, models may be developed in one cultural setting and deployed in another, leading to unforeseen consequences. We explore the effects of using...