Presented at the 2017 International Conference on Knowledge Management. This presentation examines uses knowledge discovery and text mining to identify patterns and trends in the data science discipline by examining core course titles of the Data Science curriculum offered in the United States.

Presented at the 2017 International Conference on Knowledge Management during the panel session on Big Data, Ethics and Public Engagement. This presentation discusses the Data Rescue Denton 2017 event.

Presentation for the 2017 International Conference on Knowledge Management. This presentation describes the use of text mining and visualization to identify collective memory themes in knowledge management literature.

The research seeks to know if the COVID-19 pandemic has created culture change by measuring the criteria of work outputs and actions of organization members. As a part of this research, a survey was developed to identify how and to what extent workplace culture has been impacted. 111 professional services staff from a North Texas business were surveyed. We identified three factors for criteria of work outputs and behavior that indicates the current level of change of the culture. The three factors are identified as, Expectations (α= 0.786), Accuracy (α= 0.603), and Timeliness (α= 0.552). Factor analysis and descriptive statistics are used to analyze the result from the survey.

Understanding trends is helpful to identify future behaviors in the field, and the roles of people, places, and institutions in setting those trends. Although traditional clustering strategies can group articles into topics, these techniques do not focus on topics over limited timescales; additionally, even when articles are grouped, the generated results are extensive and difficult to navigate. To address these concerns, we create an interactive dashboard that helps an expert in the field to better understand and quantify trends in their area of research. Trend detection is performed using the time-biased document clustering introduced in Behpour et al. (2021) study. The developed and freely available web application enables users to detect well defined trending topics in financial journals by experimenting with various levels of temporal bias - from detecting short-timescale trends to allowing those trends to spread over longer times. Experts can readily drill down into the identified topics to understand their meaning through keywords, example articles, and time range. Overall, the interactive dashboard will allow experts in the field to sift through the vast literature to identify the concepts, people, places, and institutions most critical to the field.

This workshop is presented by members of a University of North Texas research team. First, the team will overview their experience as members of the research team and share experience in areas such as trust formation, team roles, productivity, work-life balance, faculty-students interaction, peer and faculty mentorship, dissertation preparation, and job seeking. Second, the workshop will discuss and brainstorm how this format can be implemented for organizations both with faculty-student teams and with peer-directed teams. Finally, successes and challenges are openly discussed with audience.

Global warming is the term used to describe critical environmental issues and concerns. Social media such as Twitter provides a platform for people to share information, exchange ideas, and express their opinions about current and timely issues. This study utilized contextual analysis to analyze data collected from Twitter for the hashtag "global warming" during the period 2010 & 2011. Using sentiment analysis and topic modeling, the study aimed first at assessing people's perception towards global warming issues, and second study the impact of misinformation from the standpoint of social noise on people's perception of global warming during critical environmental events. The outcome of this study helps create a better understanding of the environmental issues discussed on social media. The sentiment analysis from the data analyzed so far shows that most of the tweets were based on Twitter users' personal opinions and not science. The topic modeling results suggest that Twitter users typically tweeted when a major environmental event occurred due to global warming. Topic modeling also aids in the identification of terms that is associated with social noise. The presence of social noise suggests that misinformation does exist and spreads faster.

Building predictive models for companies often relies on inference using historical data of companies in the same industry sector. However, companies are similar across a variety of dimensions that should be leveraged in relevant prediction problems. This is particularly true for large, complex organizations which may not be well defined by a single industry and have no clear peers. To enable prediction using company information across a variety of dimensions, we create an embedding of company stocks, Stock2Vec, which can be easily added to any prediction model that applies to companies with associated stock prices. We describe the process of creating this rich vector representation from stock price fluctuations and characterize what the dimensions represent. We then conduct comprehensive experiments to evaluate this embedding in applied machine learning problems in various business contexts. Our experiment results demonstrate that the four features in the Stock2Vec embedding can readily augment existing cross-company models and enhance cross-company predictions.