Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


David Bodoff has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A fundamental question of counting in association rules

    by David Bodoff, Marina Feldus Goldman

    Discovery association rules (D-AR) are widely used for data mining in industry, and have been extensively researched in academia. An elementary step in the calculation of the strength of each proposed rule X→Y is the tabulation of occurrences and co-occurrences of X and Y. Yet, a fundamental question does not appear to have received attention in the literature. The question is, how should one count these occurrences? Nearly all researchers and practitioners use one method, but there is actually an alternative way to count, and the data mining literature has not seriously considered the alternative or justified the prevailing choice. This fundamental question of counting is not a purely theoretical difference; the methods yield different results. In this research, we investigate the implications of the two methods. Results include the following: (1) Both methods can be correct under different probabilistic setups; (2) The two counting methods yield different results, in terms of the ranking of rules by their strengths; (3) The extent to which the methods diverge depends on properties of the data, one of which we identify; (4) Based on analytical and empirical results, we propose a set of guidelines for making a principled choice of counting method in a given study. Our research provides the basis for choosing an appropriate D-AR counting method, and improves our understanding of how this choice affects the meaning, strengths, and limitations of results.

  • On the status of machine learning inferences in data privacy economics and regulation

    by David Bodoff

    Advances in machine learning technology, combined with fantastic growth in the volume and variety of data that firms capture about individuals, have led to increased public awareness of the question of data privacy. However, as reported in the relevant literatures, the machine learning technology poses challenges to resolving these questions. The information economics literature on data privacy discusses challenges to economic modeling of the problem, due to the externalities that machine learning exhibits; the literature that uses a more regulatory approach to data privacy cites different challenges, such as widely held assumptions about a firm’s right to make inferences from their data, which create resistance to any attempts at regulation. It thus emerges that just when machine learning technology has created a need for advances in data privacy policy, the characteristics of the technology itself are hindering progress. The observation that is the point of departure for this chapter is that paradoxically, by delving a bit into some technical distinctions about how machine learning works, we are able to partially defuse these apparent stumbling blocks, or at least, sharpen our understanding of them. This chapter highlights the reported challenges to crafting data privacy policy for machine learning, and attempts, through discussion of some technical distinctions, to clarify the challenges and point to some possible ways forward.

  • Tone and credibility in voluntary disclosures

    by David Bodoff, Iris Hirsch

    Purpose: The purpose of this research paper is to study attitudinal responses to the tone of a voluntary disclosure. It is known that tone can affect market response. Existing literature assumes that investors' attitudes mediate these effects, but these attitudinal mediators have not been directly measured. The authors are especially interested in cases where a firm is reporting poor financial results. The purpose is to trace the mechanism and conditions under which tone affects the credibility of a voluntary disclosure.Design/methodology/approach: The authors conducted a 2 × 2 between-subjects study that manipulates financial performance (good/bad) and tone (positive/negative). The attitudinal dependent variable is the credibility of the management discussion, with persuasive intent as a mediator of the effects of tone on credibility.Findings: In the case of bad financial results, a positive tone has a negative effect on credibility as the authors predict. This effect is fully mediated by perceived “persuasive intent”. In the case of good financial performance, credibility is higher when management adopts a positive tone, even though there, too, subjects perceive the persuasive intent.Research limitations/implications: The research paper establishes a bridge between the communications and finance literature on the effect of tone in voluntary disclosures. The empirical findings provide initial evidence and new detail regarding an attitudinal response (credibility) that the finance literature often assumes is responsible for mediating market responses to voluntary disclosures. One unexpected finding with interesting implications is that positive tone increases credibility in the case of good news. The implication is that a firm may indulge in taking a victory lap to celebrate good news, without harming the credibility of their corporate communications. Additional research is warranted that combines theory and methods from communications and finance, to further elaborate the attitudinal mechanisms behind the market effects of tone in voluntary disclosures.Originality/value: At the most general level, the original contribution is the creation of a theoretical and methodological bridge between the communications and finance literature, regarding the effect of tone in voluntary disclosures. This research proposes an integrated theoretical framework, in which the concept of incentives shapes the relationships between the firm's financial situation, a disclosure's tone and its credibility. Methodologically, the authors employ an experimental method, which is more typical in the communications literature, to illuminate the attitudinal effects of tone that are frequently mentioned and assumed in the finance literature.


  • Open Access

    A Fundamental Question of Counting in Association Rules

    by David Bodoff, Marina Feldus Goldman

    Association Rules (AR) are widely used for data mining in industry, and have been extensively researched in academia. An elementary step in the calculation of the strength of each proposed rule X -> Y is the tabulation of occurrences and co-occurrences of X and Y. Yet, a fundamental question does not appear to have received attention in the literature. The question is, how should one count these occurrences? Nearly all researchers and practitioners use one method, but there is actually an alternative way to count, and the data mining literature has not seriously considered the alternative or justified the prevailing choice. This fundamental question of counting is not a purely theoretical difference; the methods yield different results. In this research, we investigate the implications of the two methods. Results include the following: (1) Both methods can be correct under a different probabilistic setup; (2) The two counting methods yield different results, in terms of the relative order of rules when ranked by strength; (3) The extent to which the methods diverge depends on properties of the data, one of which we identify; (4) The methods can be compared based on their properties, one of which we investigate. The contribution of our work is that it brings to light a technical choice that impacts results, and provides a few bases upon which a researcher or practitioner can make a principled choice of which method to use when employing AR.

  • Viewpoints in indexing term assignment

    by David Bodoff, Yaffa Richter‐Levin

    The literature on assigned indexing considers three possible viewpoints—the author's viewpoint as evidenced in the title, the users' viewpoint, and the indexer's viewpoint—and asks whether and which of those views should be reflected in an indexer's choice of terms to assign to an item. We study this question empirically, as opposed to normatively. Based on the literature that discusses whose viewpoints should be reflected, we construct a research model that includes those same three viewpoints as factors that might be influencing term assignment in actual practice. In the unique study design that we employ, the records of term assignments made by identified indexers in academic libraries are cross‐referenced with the results of a survey that those same indexers completed on political views. Our results indicate that in our setting, variance in term assignment was best explained by indexers' personal political views. © 2019 ASIS&T


  • Open Access

    Evolution of language: An empirical study at eBay Big Data Lab

    by David Bodoff, Ron Bekkerman, Julie Dai

    The evolutionary theory of language predicts that a language will tend towards fewer synonyms for a given object. We subject this and related predictions to empirical tests, using data from the eBay Big Data Lab which let us access all records of the words used by eBay vendors in their item titles, and by consumers in their searches. We find support for the predictions of the evolutionary theory of language. In particular, the mapping from object to words sharpens over time on both sides of the market, i.e. among consumers and among vendors. In addition, the word mappings used on the two sides of the market become more similar over time. Our research contributes to the literature on language evolution by reporting results of a truly unique large-scale empirical study.


  • Effectiveness of Website Personalization: Does the Presence of Personalized Recommendations Cannibalize Sampling of Other Items?

    by David Bodoff, Shuk Ying Ho

    With advances in personalization technologies, websites are increasingly able to customize Web content and provide users with a unique experience. Prior research has focused more on the appeal of the personalized recommendations themselves and examined user behavior toward the personalized recommendations. However, prior research has not compared the total volume of users’ sampling activity on websites that offer personalization, compared to those that do not. This motivates our interest in an extended study of the totality of users’ sampling behavior on the website when personalized recommendations are present. Where prior work has focused on the amount of sampling of the personalized items themselves, we define two additional indicators that characterize a consumer’s sampling behavior on a website that has both stock and personalized items: (1) the total volume of sampling to include both stock and personalized items, and (2) the pattern of sampling between personalized and stock items. Based on consumer search theory (CST) and a simulation analysis, we propose hypotheses about consumers’ behavior on these expanded outcomes, and test them in a longitudinal field study. We find that subjects sample personalized items before stock items, and sample fewer items in total when personalized recommendations are available. In addition, subjects engage in less sampling as time goes on, across sessions. Theoretically, this research brings the CST perspective to the literature on website personalization. Practically, this research sheds light on the precise nature of the benefit and possible drawbacks of personalization from the merchant’s perspective.


  • Priming Effects and Strategic Influences in Social Tagging

    by David Bodoff, Eran Vaknin

    In many social tagging systems, users can see the tags already created by others. Prior research has shown that this exposure leads users to create tags that are semantically related to the previous ones. We investigate two possible mechanisms through which this occurs, semantic priming and strategic choice. Semantic priming occurs when an existing tag subconsciously primes the user’s mind to suggest semantically related tags. In an experiment, no such effect is found, in contrast to prior research. A follow-up study shows that whether semantic priming occurs depends on whether the person uses others’ previously created tags or is just passively exposed to them. The second type of influence, strategic choice, occurs in ESP-type settings. It refers to behavior in which a user chooses words that are semantically related to an existing tag in order to increase the chances of matching one’s partner. Experimental results provide clear evidence of this strategic influence. In a follow-up study, we demonstrate that there is a meaningful difference in the tag sets that are created under the influence of strategic choice. Our work sheds light on the conditions and mechanisms through which existing tags influence subsequent tagging behavior.


  • Question types and intermediary elicitations

    by David Bodoff, Daphne Raban

    In the context of online question‐answering services, an intermediary clarifies the user's needs by eliciting additional information. This research proposes that these elicitations will depend on the type of question. In particular, this research explores the relationship between three constructs: question types, elicitations, and the fee that is paid for the answer. These relationships are explored for a few different question typologies, including a new kind of question type that we call Identity. It is found that the kinds of clarifications that intermediaries elicit depend on the type of question in systematic ways. A practical implication is that interactive question‐answering services—whether human or automated—can be steered to focus attention on the kinds of clarification that are evidently most needed for that question type. Further, it is found that certain question types, as well as the number of elicitations, are associated with higher fees. This means that it may be possible to define a pricing structure for question‐answering services based on objective and predictable characteristics of the question, which would help to establish a rational market for this type of information service. The newly introduced Identity question type was found to be especially reliable in predicting elicitations and fees.


  • Top Cited Papers

    The Effects of Web Personalization on User Attitude and Behavior: An Integration of the Elaboration Likelihood Model and Consumer Search Theory1

    by Shuk Ying Ho, David Bodoff

    Web personalization can achieve two business goals: increased advertising revenue and increased sales revenue. The realization of the two goals is related to two kinds of user behavior: item sampling and item selection. Prior research does not provide a model of attitude formation toward a personalization agent nor of how attitudes relate to these two behaviors. This limits our understanding of how web personalization can be managed to increase advertising revenues and/or sales revenues. To fill this gap, the current research develops and tests a theoretical model of user attitudes and behaviors toward a personalization agent. The model is based on an integration of two theories: the elaboration likelihood model (ELM) and consumer search theory (CST). In the integrated model, a user’s attitude toward a personalization agent is influenced by both the number of items he/she has sampled so far (from CST) and the degree to which he/she cognitively processes each one (from ELM). In turn, attitude is modeled to influence both behaviors—that is, item selection and any further item sampling. We conducted a lab study and a field study to test six hypotheses. This research extends the theory on web personalization by providing a more complete picture of how sampling and processing of personalized recommendations influence a user’s attitude and behavior toward the personalization agent. For online merchants, this research highlights the trade-off between item sampling and item selection and provides practical guidance on how to steer users toward the attitudes and behaviors that will realize their business goals.