Business Analytics Commons^™

Swift/Kelce Star Power Effect? Engagement Created A 96% Increase In Nfl Discussion Online With 82% Of Social Media Posts Expressing “Joy” About The Couple, Yi Luo, Jin-A Choi, Bond Benton

College of Communication and Media Scholarship and Creative Works

On August 27, 2025, Grammy winning singer Taylor Swift and football champion Travis Kelce announced their engagement. Celebrity couples inspire popular reactions with commercial implications. A research study from the Joetta Di Bella and Fred C. Sautter III Center for Strategic Communication in the College of Communication and Media at Montclair State University analyzed online reaction in the period immediately after the power couple’s engagement was announced. Results suggest overwhelming interest, positivity, and potential benefits to major brands, such as the National Football League. Findings include a 96% increase in brand references for the NFL and Kansas Chiefs on social …

Collecting Financial Data From Online Sources: Enhancing Large Language Models With Real-Time Search, Yang Li

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Timely and accurate access to financial data is crucial for empirical research in accounting and finance. However, current data collection processes are often manual, inconsistent, and difficult to scale. This study asks: How can large language models (LLMs) be effectively used to automate financial data collection? Using design science research methodology (DSRM), the author develops a modular architecture that integrates a real-time search API and auxiliary information processing into LLM workflows. The study applies the model to two tasks: extracting ESG report release dates and identifying customer firm tickers from COMPUSTAT. The system achieves 96% and 95% accuracy, respectively, comparable …

Llm-Guided Multimodal Information Fusion With Hierarchical Spatio-Temporal Graph Network For Sentiment Analysis, Yujie Jin, Yong Wang, Yuzhe Wang, Qiyang Chen, Bin Hu, Yanling Han, Chaoyin Ma, Witold Pedrycz

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Multimodal sentiment analysis aims to attain a precise comprehension of emotions by integrating complementary textual, visual, and audio information. However, issues such as sentiment discrepancies between modalities, ineffective integration of multi-modal information, and the intricacy of order dependency significantly constrain the models' efficacy. The authors propose an LLM-guided Hierarchical Spatio-Temporal Graph Network (L-HSTGN). By multimodal large model feature enhancement, bidirectional spatio-temporal joint modeling, and dynamic gate fusion mechanism, they effectively address the aforementioned problems. Firstly, they produce cross-modal emotion pseudo-labels based on the multimodal large model, and the single-modal representation was optimized by combining adversarial regularization. Secondly, they develop a …

Guinness Is The "Pumpkin Spice Latte" Of St. Patrick's Day, Jin-A Choi, Bond Benton, Yi Luo

College of Communication and Media Scholarship and Creative Works

This study by a team of faculty from the Joetta Di Bella and Fred C. Sautter III Center for Strategic Communication in the School of Communication and Media at Montclair State University shows that Guinness was the most-discussed brand on social media leading up to St. Patrick’s Day, and not just in the traditional ways people share how they drink the popular beer brand. The volume of social media conversations related to Guinness beer and St. Patrick’s Day saw a 25% increase. Most social chats exhibited a happy mood as evidenced by a 62% joyful sentiment.

While the Shamrock Shake …

An Investigation Of Social Media Discussion On Valentine's Day 2024 Trends: Money Can Buy Love And Chocolates, Jin-A Choi, Bond Benton, Yi Luo

College of Communication and Media Scholarship and Creative Works

Valentine’s Day, typically defined by expression of love and affection, has been celebrated as a symbolic day to exchange gifts among lovers. The expression of love has been firmly tied with the act of giving material things, such as gifts. However, over the years, discomfort and even anger has grown around the over-commercialization of Valentine’s Day, creating a deep divide between those who gift and those who criticize and denounce the holiday as nothing but a “Hallmark card holiday” to push consumerism. Our center’s study from the previous year indicated that over-commercialization of Valentine’s Day found that love is not …

Taylor-Made Super Bowl: Taylor Swiftmania On Social Media Regarding The Big Game, Yi Luo, Jin-A Choi, Bond Benton

College of Communication and Media Scholarship and Creative Works

Celebrity couples occupy a unique space in popular culture. Similar to the royal unions of history and the present, the combination of notoriety and the voyeuristic appeal of watching a relationship play out in public spaces, celebrity couples energize popular discourse and invite public commentary and interest. The opportunity to become a spectator in ongoing celebrity coupling invites a level of perceived intimacy in what feels like a relationship with famous people.

Data collected for this study suggests Taylor Swift’s connection to Super Bowl LVIII has elevated the meaning of the game beyond the stratospheric levels of cultural significance the …

Learning-By-Doing In Non-Homogeneous Tasks: An Empirical Study Of Content Creator Performance On A Music Streaming Platform, Yang Li, Yanni Ping, Yuyun Zhong, Ram Misra

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

With the development of high-speed internet and better mobile connections, online streaming platforms with user-generated videos are becoming popular. The success of these platforms relies on content creators who can effectively enhance user engagement (e.g., subscribing to a content creator’s channel). As opposed to homogeneous production scenarios (e.g., assembling automobiles in a factory), creating user-generated videos is a more complex task in which learning might happen. In this study, we empirically test the effect of prior experience on content creators’ performance. Furthermore, we examine the role of specialization in learning. We use a dataset from NetEase Cloud Music, one of …

Tree-Based Algorithm For Stable And Efficient Data Clustering, Hasan Aljabbouli, Abdullah Albizri, Antoine Harfouche

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

The K-means algorithm is a well-known and widely used clustering algorithm due to its simplicity and convergence properties. However, one of the drawbacks of the algorithm is its instability. This paper presents improvements to the K-means algorithm using a K-dimensional tree (Kd-tree) data structure. The proposed Kd-tree is utilized as a data structure to enhance the choice of initial centers of the clusters and to reduce the number of the nearest neighbor searches required by the algorithm. The developed framework also includes an efficient center insertion technique leading to an incremental operation that overcomes the instability problem of the K-means …

Data Quilting: Art And Science Of Analyzing Disparate Data, Murugan Anandarajan, Chelsey Hill

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Motivated by incongruences between today’s complex data, problems and requirements and available methodological frameworks, we propose data quilting as a means of combining and presenting the analysis of multiple types of data to create a single cohesive deliverable. We introduce data quilting as a new analysis methodology that combines both art and science to address a research problem. Using a three-layer approach and drawing on the comparable and parallel process of quilting, we introduce and describe each layer: backing, batting and top. The backing of the data quilt is the research problem and method, which supports the upper layers. The …

Subjectivity Of Diamond Prices In Online Retail: Insights From A Data Mining Study, Stanislav Mamonov, Tamilla Triantoro

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Diamonds belong to a unique product category whose perceived value is largely dependent on socially constructed beliefs. To explore the degree to which the physical properties of a diamond can be used to predict the diamond price, we perform data mining on a large dataset of loose diamonds scraped from an online diamond retailer. We find that diamond weight, color and clarity are the key characteristics that influence diamond prices. The data mining results also suggest a high degree of subjectivity in diamond pricing that may reflect price obfuscation strategies employed by diamond retailers.

Using Financial Investment Measures To Proactively Engage Students In The Introductory Business Statistics Course, Mark L. Berenson, Nicole Koppel, Richard Lord, Laura L. Chapdelaine

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Typically, the core-required undergraduate business statistics course covers a broad spectrum of topics with applications pertaining to all functional areas of business. The recently updated American Statistical Association's GAISE (Guidelines for Assessment and Instruction in Statistics Education) College Report once again stresses the pedagogical importance of topic and application relevancy in an increasingly data-centered world. To this end, only two introductory textbooks have incorporated some financial investment measures (Sharpe ratio and beta coefficient) in the teaching of numerical descriptive measures and simple linear regression analysis, respectively, while a few others include them as real-data application exercises at the end of …

The Emerging International Taxation Problems, James G. Yang, Victor N.A. Metallo

Department of Accounting and Finance Faculty Scholarship and Creative Works

The problems of tax evasion and tax avoidance are as old as taxes themselves. Between 2015 and 2016 alone, many U.S. multinational corporations were involved in tax disputes with the European Commission. From a historical perspective, these disputes are unprecedented as they have resulted in tremendous amount of tax penalties. The most notable case was Apple for €13 billion of unpaid tax. This article discusses what tax strategies these corporations used that caused such disputes. It specifically investigates seven corporations: Apple Inc., McDonald’s, Starbucks, Fiat, Amazon, Google, and Ikea, and elaborates on the following tax strategies: high royalties, intercompany transfer …

The Role Of User Psychological Contracts In The Sustainability Of Social Networks, Stanislav Mamonov, Marios Koufaris, Raquel Benbunan-Fich

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Many emergent ventures, such as social networks, leverage crowd-sourced information assets as essential pillars supporting their business models. The appropriation of rights to information assets through legal contracts often fails to prevent conflicts between the users and the companies that claim information rights. In this paper, we focus on social networks and examine why those conflicts arise and what their consequences are by drawing on psychological contract theory. We propose that intellectual property and privacy expectancies comprise core domains of psychological contracts between social networks and their users. In turn, perceived breaches of those expectancies trigger a psychological contract violation. …

Responding To State Sales Tax Laws For Online Retailers - A Case Study Of Amazon And The States, Ross Malaga

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

As state budgets have come under increasing pressure, many states have enacted so called "Amazon taxes" that seek to have large online retailers collect state sales tax. States are attempting to expand the concept of nexus to include marketing affiliates and corporate subsidiaries. Amazon and other large retailers have reacted in different ways depending on the state and the specific legislation. This paper discusses the potential impact of these new laws and how both states and online retailers have dealt with the issues involved.

Using Van Valens Procedure In Business Research To Assess Consistent Differences In Multidimensional Variability In Two Or More Groups, Mark L. Berenson, Kimberly Killmer Hollister

Department of Information Management and Business Analytics Faculty Scholarship and Creative Works

Much business research involves comparisons in two or more groups on many dimensions. This paper primarily focuses on demonstrating and providing guidance as to how researchers should approach a multivariate analysis in the comparison of sets of corresponding characteristics in two or more independent groups. In particular, this paper demonstrates the utility of a simple but not widely known procedure developed by Van Valen (1978) that should be employed to test for the significance of differences in overall variability in the sets of corresponding characteristics in two or more groups, a test that enjoys much statistical power in detecting significant …