Predicting human behavior: The next frontiers

Abstract

Machine learning has provided researchers with new tools for understanding human behavior. In this article, we briefly describe some successes in predicting behaviors and describe the challenges over the next few years.A dvances in machine learning are revolutionizing how we understand offline and online human behavior. The ability to classify objects of interest from a training set, whether those objects are terrorists (1), machines that need maintenance (2), or emails containing a malicious link (3), represents the greatest success in the field. Typically, no single machine learning algorithm does everything well. Although accuracy is crucial, the acceptable accuracy varies with the problem being studied, and accuracy is not enough. All too often, researchers explain why their predictions are right but say nothing about why their predictions might be wrong. Knowing both enables decision-makers to make better decisions. Especially in high-risk situations, predictions must have accompanying explanations that provide deeper understanding of the situation being studied. A predictive model must also provide one or more prescriptions for potential future actions that enable decision-makers to make better decisions. Today's machine learning methods do not necessarily satisfy these three criteria. What constitutes an ideal predictive algorithm depends on the application. Oftentimes, stakeholders (e.g., social media platforms and search engines) will use varying definitions of accuracy that meet their particular needs. Moreover, domain experts may use extensive knowledge of the domain to suggest relevant independent variables to be included in a data set. Often, they will explain predictions using both the technical accuracy measures generated by a predictive model and stories from their discipline that are more understandable to their audiences. All of this suggests that in real-world systems, computer scientists need to team with stakeholders to generate high-impact results.In our opinion, the next generation of predictive models must deal with four major challenges.First, the maxim that more data lead to better predictive models is not always true, because noise in the data can overwhelm predictive models. The ability to deal with noisy, incomplete, and inconsistent data will be at the heart of nextgeneration predictive models. For instance, when identifying "bots" on Twitter (4) that are seeking to sway opinion to be positive about a political candidate, we needed to ignore the huge numbers of bots that were seeking to achieve other ends-such as spreading spam or seeking to influence opinions about other topics or to deceive users into clicking on links that generate revenue for the person who included that link in their tweet. Moreover, data about many Twitter handles are limited and, in some cases, intentionally misleading. Bot developers go to considerable effort to ensure that their bots elude detection.A second challenge is that of rare-event prediction. For instance, companies monitoring their internal networ...

Detecting Fake News on Social Media

“…Thus, capturing users' profiles and characteristics as weak social supervision can provide useful information for fake news detection. User behaviors can indicate their characteristics [8] who have interactions with the news on social media. These features can be categorized in different levels: individual level and group level.…”

The power of noise and the art of prediction

“…Most studies using single best models explain why their models are the best, but say little or nothing about how or why their predictions or inferences might be wrong (Subrahmanian and Kumar, 2017). To demonstrate the risks of taking this approach, we have shown both.…”

Toward an Agent-Agnostic Transmission Model: Synthesizing Anthropocentric and Technocentric Paradigms in Communication

“…states" (Pentland & Liu, 1999, p. 229)-and as biological machines with a talent for semantics over syntax (Searle, 1990). Human behavior relies, to an extent, on (semi-)invariant rules and algorithms for how language, reasoning, and behaviors in relation to these states (e.g., such as encoding and decoding of symbols and reliance on cognitive shortcuts; Simon, 1990), such that human behavior can be computationally modeled and predicted (Subrahmanian & Kumar, 2017). Specific to communication behaviors, human-authored digital messages are both produced and consumed as entertainment-as informational or experiential assets-rather than necessarily according to socioemotional drives, as with the commodification of personal information inherent to dating apps (Hobbs et al, 2017).…”