Published work

Cross-Platform Spillover Effects in Consumption of Viral Content: A Quasi-Experimental Analysis Using Synthetic Controls

Haris Krijestorac, Rajiv Garg, and Vijay Mahajan

Published in Information Systems Research (2020)

Decisions Under the Illusion of Objectivity: Digital Embeddedness and B2B Purchasing

Haris Krijestorac, Rajiv Garg, and Prabhudev Konana

Published in Production and Operations Management (2021)

Working Papers

Personality-Based Content Engineering for Rich Digital Media

Haris Krijestorac, Rajiv Garg, and Maytal Saar-Tsechansky

In Progress

To Use or Not to Use Samuel L. Jackson? The Role of Acoustic Vocal Characteristics on Consumer Decisions

Haris Krijestorac, Rajiv Garg, and Vijay Mahajan


With the rise of voice-based digital interfaces, such as Alexa and Siri, firms are increasingly leveraging voice to market products. Indeed, voice AI devices have invested in hiring speech actors, including prominent figures such as Samuel L. Jackson. However, it remains unclear whether the success of a voice like that of Jackson is due to its unique acoustic properties (e.g., pitch, loudness, tempo), and what contextual factors inform the effectiveness of such a voice. Our research explores the effect of acoustic properties of voice on consumer decisions related to utilitarian and hedonic products. To achieve this, we empirically identify and label six generalizable voice clusters, based on eight stochastic acoustic features of 571 voices. We then present 290 subjects with voice ads generated by the Google Voice API, using pre-written scripts for hedonic and utilitarian product ads. Based on reactions to these ads collected in a survey, we find that while “ostentatious” voices tend to be more effective, those that are “seductive” are less effective. Meanwhile, voices that are “suave” and “colloquial” are more effective for hedonic products only. We discuss implications for voice AI devices and voice actors, voice personalization, and future directions for voice analytics.

The Role of Emotional Arcs in Generating User Engagement on Social Media Platforms

Reza Alibakhshi, Haris Krijestorac, and Shirish Srivastava


As social media platforms containing short-form videos (e.g., Instagram, Snapchat, TikTok) gain traction, a challenge for content creators is converting passive consumption of these media (views), which is plentiful, into active engagement (likes), which is comparatively rare. Prior studies have demonstrated that narrative arcs, whether in the context of movies or sports, are key to stimulating engagement when these media are consumed. Building on this, our study explores how designing appropriate “emotional arcs” (i.e., expressions of various emotions over time) may help convert views of Instagram videos into likes. Using a dataset of 765 videos from 80 corporate Instagram accounts, we employ machine learning techniques to extract levels of expression of five key emotions over time within these videos. Using an ensemble of empirical approaches, we demonstrate that emotional arcs have significant predictive power over the engagement rate in Instagram videos, and are thus meaningful in stimulating engagement in the context of short-form videos. Moreover, we unpack the black box to explore which emotional arcs are effective and ineffective, and support these findings through causal analysis. Moreover, we label and describe these arcs with examples to provide prescriptive insights for content creators. We discuss the implications of these findings for online content creators, marketers, and platforms.