Panagiotis Adamopoulos
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
Research Subjects
Panagiotis Adamopoulos has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Alexander Tuzhilin
New York University
3 shared publicationsVilma Todri
Emory University
3 shared publicationsAnindya Ghose
Stern School of Business, New York University, New York, New York 10012; and Korea University Business School, Korea University, Seoul 136-701, South Korea
2 shared publications- Anindya Ghose
Leonard N. Stern School of Business, New York University, New York, New York 10012
2 shared publications - Vilma Todri
Goizueta Business School, Emory University, Atlanta, Georgia 30322
2 shared publications - Alejandro Bellogín
Universidad Autónoma de Madrid, Madrid, Spain
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9526-9529
GRAIL 2026: Workshop on Generative, Retrieval-augmented, and Agentic Intelligence for Personalization
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9526-9529
Open AccessGRAIL 2026: Workshop on Generative, Retrieval-augmented, and Agentic Intelligence for Personalization
- 1 December 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 70 (12) , 8818-8832
The Spillover Effect of Fraudulent Reviews on Product Recommendations
As the prevalence of user-generated reviews has been growing, the pervasiveness of fraudulent reviews has been increasing as well. In an effort to alleviate the consequences of fraudulent reviews, platforms have been using machine-learning algorithms for fraudulent review detection. However, the current business practice of simply removing fraudulent reviews might not be sufficient, as even their temporary presence might forge spillover effects propagating through other shopping tools. In particular, we examine and discover the persistence of long-lasting significant adverse impact of fraudulent reviews through their propagation to recommender systems, even long after successfully detecting and removing all fraud incidents. We conduct additional analyses further examining the intensity and evolution of the spillover effect over time across different dimensions, such as the cost of the fraudulent activity, the effectiveness and timeliness of the detection algorithms, and the quality of products. The results illustrate the gravity of the identified effect and highlight that the current business practice of just removing the fraudulent reviews is insufficient in the presence of recommender systems, albeit potentially sufficient in their absence in the long run. Such findings are timely as they might inform current regulatory and policy discussions. Finally, we also design a simple remedy that can be easily introduced to collaborative filtering algorithms to debias the recommender systems and demonstrate its effectiveness in alleviating the impact of the identified spillover effect. This paper was accepted by D. J. Wu, information systems. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.02612 .
- 1 December 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 70 (12) , 8818-8832
The Spillover Effect of Fraudulent Reviews on Product Recommendations
As the prevalence of user-generated reviews has been growing, the pervasiveness of fraudulent reviews has been increasing as well. In an effort to alleviate the consequences of fraudulent reviews, platforms have been using machine-learning algorithms for fraudulent review detection. However, the current business practice of simply removing fraudulent reviews might not be sufficient, as even their temporary presence might forge spillover effects propagating through other shopping tools. In particular, we examine and discover the persistence of long-lasting significant adverse impact of fraudulent reviews through their propagation to recommender systems, even long after successfully detecting and removing all fraud incidents. We conduct additional analyses further examining the intensity and evolution of the spillover effect over time across different dimensions, such as the cost of the fraudulent activity, the effectiveness and timeliness of the detection algorithms, and the quality of products. The results illustrate the gravity of the identified effect and highlight that the current business practice of just removing the fraudulent reviews is insufficient in the presence of recommender systems, albeit potentially sufficient in their absence in the long run. Such findings are timely as they might inform current regulatory and policy discussions. Finally, we also design a simple remedy that can be easily introduced to collaborative filtering algorithms to debias the recommender systems and demonstrate its effectiveness in alleviating the impact of the identified spillover effect. This paper was accepted by D. J. Wu, information systems. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.02612 .
- 25 July 2024
- Published by SAGE Publications in Production and Operations Management
- Vol. 34 (12) , 4015-4038
Consumer Social Connectedness and Persuasiveness of Collaborative-Filtering Recommender Systems: Evidence From an Online-to-Offline Recommendation App
Consumers often rely on their social connections or social technologies, such as (automated) system-generated recommender systems, to navigate the proliferation of diverse products and services offered in online and offline markets and cope with the corresponding choice overload. In this study, we investigate the relationship between the consumers’ social connectedness and the economic impact of recommender systems. Specifically, we examine whether the social connectedness levels of consumers moderate the effectiveness of online recommendations toward increasing product demand levels. We study this novel research question using a combination of datasets and a demand-estimation model. Interestingly, the empirical results show a positive moderating effect of social connectedness on the demand effect of online-to-offline recommendations. Further delving into the findings, we also provide empirical evidence that social identification might explain why denser social connectedness with local users accentuates the effects of collaborative-filtering online-to-offline recommendations. Our study enhances the understanding of community factors affecting the efficacy of social technologies in multichannel operations while also extending the social identity theory in operations in the digital realm. The results also have intriguing operational implications for operations managers and practitioners, while suggesting several interesting avenues for future research on social technologies and operations management.
- 25 July 2024
- Published by SAGE Publications in Production and Operations Management
- Vol. 34 (12) , 4015-4038
Consumer Social Connectedness and Persuasiveness of Collaborative-Filtering Recommender Systems: Evidence From an Online-to-Offline Recommendation App
Consumers often rely on their social connections or social technologies, such as (automated) system-generated recommender systems, to navigate the proliferation of diverse products and services offered in online and offline markets and cope with the corresponding choice overload. In this study, we investigate the relationship between the consumers’ social connectedness and the economic impact of recommender systems. Specifically, we examine whether the social connectedness levels of consumers moderate the effectiveness of online recommendations toward increasing product demand levels. We study this novel research question using a combination of datasets and a demand-estimation model. Interestingly, the empirical results show a positive moderating effect of social connectedness on the demand effect of online-to-offline recommendations. Further delving into the findings, we also provide empirical evidence that social identification might explain why denser social connectedness with local users accentuates the effects of collaborative-filtering online-to-offline recommendations. Our study enhances the understanding of community factors affecting the efficacy of social technologies in multichannel operations while also extending the social identity theory in operations in the digital realm. The results also have intriguing operational implications for operations managers and practitioners, while suggesting several interesting avenues for future research on social technologies and operations management.
- 1 December 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 34 (4) , 1533-1553
The Decoy Effect and Recommendation Systems
Recommendation systems and the decoy effect are two popular marketing techniques that have been used for facilitating decision making. Practitioners often use decoys to help drive demand for specific items, and prior research has shown the decoy effect to be robust in traditional choice settings, with consistent reporting of an overall positive impact. Recommendation systems are also increasingly being used to present item choice sets to customers and users, assisting users in their decision-making process. However, previous work has not examined the decoy effect in the context of recommendations. The decoy effect may facilitate consumer decision making and positively impact user behavior when used with recommendation systems. However, in the recommendation context, customers often have different expectations for the reliability and quality of the presented information. Hence, a decoy as a recommendation could signal issues in system reliability, resulting in a negative effect. Our study demonstrates that depending on the recommendation context, the decoy effect can be beneficial or counterproductive. Specifically, we find in the personalized context, including a decoy minimizes the demand for the target option and pushes consumers to opt out of purchase, which deviates from the traditional decoy effect. However, a decoy increases the target item’s demand in the nonpersonalized context, following the conventional decoy effect.
- 1 December 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 34 (4) , 1533-1553
The Decoy Effect and Recommendation Systems
Recommendation systems and the decoy effect are two popular marketing techniques that have been used for facilitating decision making. Practitioners often use decoys to help drive demand for specific items, and prior research has shown the decoy effect to be robust in traditional choice settings, with consistent reporting of an overall positive impact. Recommendation systems are also increasingly being used to present item choice sets to customers and users, assisting users in their decision-making process. However, previous work has not examined the decoy effect in the context of recommendations. The decoy effect may facilitate consumer decision making and positively impact user behavior when used with recommendation systems. However, in the recommendation context, customers often have different expectations for the reliability and quality of the presented information. Hence, a decoy as a recommendation could signal issues in system reliability, resulting in a negative effect. Our study demonstrates that depending on the recommendation context, the decoy effect can be beneficial or counterproductive. Specifically, we find in the personalized context, including a decoy minimizes the demand for the target option and pushes consumers to opt out of purchase, which deviates from the traditional decoy effect. However, a decoy increases the target item’s demand in the nonpersonalized context, following the conventional decoy effect.
- 1 June 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 33 (2) , 429-445
Predicting Stages in Omnichannel Path to Purchase: A Deep Learning Model
The proliferation of omnichannel practices and emerging technologies opens up new opportunities for companies to collect voluminous data across multiple channels. This study examines whether leveraging omnichannel data can lead to, statistically and economically, significantly better predictions on consumers’ online path-to-purchase journeys, given the intrinsic fluidity in and heterogeneity brought forth by digital transformation of traditional marketing. Using an omnichannel data set that captures consumers’ online behavior in terms of their website browsing trajectories and their offline behavior in terms of physical location trajectories, we predict consumers’ future path-to-purchase journeys based on their historical omnichannel behaviors. Using a state-of-the-art deep-learning algorithm, we find that using omnichannel data can significantly improve our model’s predictive power. This enhanced predictive power benefits various heterogeneous online firms, regardless of their size, offline presence, mobile app availability, or whether they are selling single- or multi-category products. Using an illustrative example of targeted marketing, we further quantify the economic value of the improved predictive power and the value of data.
- 1 June 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 33 (2) , 429-445
Predicting Stages in Omnichannel Path to Purchase: A Deep Learning Model
The proliferation of omnichannel practices and emerging technologies opens up new opportunities for companies to collect voluminous data across multiple channels. This study examines whether leveraging omnichannel data can lead to, statistically and economically, significantly better predictions on consumers’ online path-to-purchase journeys, given the intrinsic fluidity in and heterogeneity brought forth by digital transformation of traditional marketing. Using an omnichannel data set that captures consumers’ online behavior in terms of their website browsing trajectories and their offline behavior in terms of physical location trajectories, we predict consumers’ future path-to-purchase journeys based on their historical omnichannel behaviors. Using a state-of-the-art deep-learning algorithm, we find that using omnichannel data can significantly improve our model’s predictive power. This enhanced predictive power benefits various heterogeneous online firms, regardless of their size, offline presence, mobile app availability, or whether they are selling single- or multi-category products. Using an illustrative example of targeted marketing, we further quantify the economic value of the improved predictive power and the value of data.
- 1 March 2021
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 32 (1) , 238-267
Demand Effects of the Internet-of-Things Sales Channel: Evidence from Automating the Purchase Process
The internet of things (IoT) is rapidly becoming one of the most popular emerging technologies in business and society. One of the major verticals that has recently begun to effectively use IoT technologies is the retail industry. Given the unprecedented opportunities IoT generates for brands and retailers, it is important to glean timely insights regarding the business value of IoT and understand whether the introduction of an IoT technology as an alternative purchase channel for consumers affects the sales of physical products. Using empirical data from a multinational online retailer who adopted an IoT technology that largely automates the consumers’ purchases and employing a quasi-experimental framework, we study the effect of the introduction of IoT as an alternative sales channel on product sales. Our analyses reveal a statistically and economically significant increase in sales and demonstrate the business value of the IoT channel for retailers and brands. In addition, we conduct other analyses of IoT to delve into the effect of heterogeneity and empirically validate the underlying mechanisms by examining the impact of IoT for products in different price ranges, levels of substitutability, and product categories. For instance, our analyses reveal that less expensive and more differentiated products, as well as experience and utilitarian goods, can accrue higher benefits leveraging more effectively novel IoT technologies. This is the first paper to study the impact of an IoT technology on product sales, drawing important implications for devices and technologies largely automating the purchase process.
- 1 March 2021
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 32 (1) , 238-267
Demand Effects of the Internet-of-Things Sales Channel: Evidence from Automating the Purchase Process
The internet of things (IoT) is rapidly becoming one of the most popular emerging technologies in business and society. One of the major verticals that has recently begun to effectively use IoT technologies is the retail industry. Given the unprecedented opportunities IoT generates for brands and retailers, it is important to glean timely insights regarding the business value of IoT and understand whether the introduction of an IoT technology as an alternative purchase channel for consumers affects the sales of physical products. Using empirical data from a multinational online retailer who adopted an IoT technology that largely automates the consumers’ purchases and employing a quasi-experimental framework, we study the effect of the introduction of IoT as an alternative sales channel on product sales. Our analyses reveal a statistically and economically significant increase in sales and demonstrate the business value of the IoT channel for retailers and brands. In addition, we conduct other analyses of IoT to delve into the effect of heterogeneity and empirically validate the underlying mechanisms by examining the impact of IoT for products in different price ranges, levels of substitutability, and product categories. For instance, our analyses reveal that less expensive and more differentiated products, as well as experience and utilitarian goods, can accrue higher benefits leveraging more effectively novel IoT technologies. This is the first paper to study the impact of an IoT technology on product sales, drawing important implications for devices and technologies largely automating the purchase process.
- 1 January 2020
- Published by Wolters Kluwer Health in Anesthesia & Analgesia
- Vol. 130 (1) , 141-150
Chronic Atypical Antipsychotic Use Is Associated With Reduced Need for Postoperative Nausea and Vomiting Rescue in the Postanesthesia Care Unit: A Propensity-Matched Retrospective Observational Study
BACKGROUND: Atypical antipsychotics are efficacious for chemoprophylaxis against chemotherapy-induced nausea and vomiting, but perioperative investigations have been scant. We sought to examine the association between chronic atypical antipsychotic therapy and the likelihood of postoperative nausea and vomiting. METHODS: In this single-center, propensity-matched, retrospective, observational study, elective noncardiac surgical cases from January 2014 to December 2017 were examined with regard to the primary outcome of rescue antiemetic administration in the postanesthesia care unit as a measure of postoperative nausea and vomiting. Chronic administration of olanzapine, aripiprazole, and risperidone was the exposure of interest. Other independent variables included outpatient antiemetics, modified Apfel score, age, American Society of Anesthesiologists physical status score, case length, and exposures to emetogenic and chemoprophylactic agents. Logistic regression was performed using case-level data. Conditional logistic regression was performed after 1:2 propensity matching, sampling without replacement. Monte Carlo simulation was performed to compute the mean patient-level treatment effect on the treated. RESULTS: Of 13,660 cases, 154 cases with patients receiving atypical antipsychotics were matched against 308 cases without, representing 115 and 273 unique patients, respectively. In a well-balanced cohort, the mean patient-level odds of being administered rescue antiemetic was lower for patients chronically taking the 3 atypical antipsychotics under consideration as compared to those not on atypical antipsychotics, with an odds ratio of 0.29 (95% CI, 0.11–0.75; P = .015). CONCLUSIONS: Chronic atypical antipsychotic therapy is associated with reduced risk of postanesthesia care unit antiemetic administration. These findings support the need for prospective studies to establish the safety and efficacy of postoperative nausea and vomiting chemoprophylaxis with these agents.
- 1 January 2020
- Published by Wolters Kluwer Health in Anesthesia & Analgesia
- Vol. 130 (1) , 141-150
Chronic Atypical Antipsychotic Use Is Associated With Reduced Need for Postoperative Nausea and Vomiting Rescue in the Postanesthesia Care Unit: A Propensity-Matched Retrospective Observational Study
BACKGROUND: Atypical antipsychotics are efficacious for chemoprophylaxis against chemotherapy-induced nausea and vomiting, but perioperative investigations have been scant. We sought to examine the association between chronic atypical antipsychotic therapy and the likelihood of postoperative nausea and vomiting. METHODS: In this single-center, propensity-matched, retrospective, observational study, elective noncardiac surgical cases from January 2014 to December 2017 were examined with regard to the primary outcome of rescue antiemetic administration in the postanesthesia care unit as a measure of postoperative nausea and vomiting. Chronic administration of olanzapine, aripiprazole, and risperidone was the exposure of interest. Other independent variables included outpatient antiemetics, modified Apfel score, age, American Society of Anesthesiologists physical status score, case length, and exposures to emetogenic and chemoprophylactic agents. Logistic regression was performed using case-level data. Conditional logistic regression was performed after 1:2 propensity matching, sampling without replacement. Monte Carlo simulation was performed to compute the mean patient-level treatment effect on the treated. RESULTS: Of 13,660 cases, 154 cases with patients receiving atypical antipsychotics were matched against 308 cases without, representing 115 and 273 unique patients, respectively. In a well-balanced cohort, the mean patient-level odds of being administered rescue antiemetic was lower for patients chronically taking the 3 atypical antipsychotics under consideration as compared to those not on atypical antipsychotics, with an odds ratio of 0.29 (95% CI, 0.11–0.75; P = .015). CONCLUSIONS: Chronic atypical antipsychotic therapy is associated with reduced risk of postanesthesia care unit antiemetic administration. These findings support the need for prospective studies to establish the safety and efficacy of postoperative nausea and vomiting chemoprophylaxis with these agents.
- Top Cited Papers
- 1 September 2018
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 29 (3) , 612-640
The Impact of User Personality Traits on Word of Mouth: Text-Mining Social Media Platforms
Word of mouth (WOM) plays an increasingly important role in shaping consumers’ behavior and preferences. In this paper, we examine whether latent personality traits of online users accentuate or attenuate the effectiveness of WOM in social media platforms. To answer this question, we leverage machine-learning methods in combination with econometric techniques utilizing a novel quasi-experiment. Our analysis yields two main results. First, there is a positive and statistically significant effect of the level of personality similarity between two social media users on the likelihood of a subsequent purchase from a recipient of a WOM message after exposure to the WOM message of the sender. In particular, exposure to WOM messages from similar users in terms of personality, rather than dissimilar users, increases the likelihood of a postpurchase by 47.58%. Second, there are statistically significant effects of specific pairwise combinations of personality characteristics of senders and recipients of WOM messages on the effectiveness of WOM. For instance, introverted users are responsive to WOM, in contrast to extroverted users. Besides this, agreeable, conscientious, and open social media users are more effective disseminators of WOM. In addition, WOM originating from users with low levels of emotional range affects similar users, whereas for high levels of emotional range, increased similarity usually has the opposite effect. The examined effects are also of significant economic importance, as, for instance, a WOM message from an extrovert user to an introvert peer increases the likelihood of a subsequent purchase by 71.28%. Our findings are robust to several alternative methods and specifications, such as controlling for latent user homophily and network structure roles based on deep-learning models. By extending the characteristics that have been theorized to affect the effectiveness of WOM from the observable to the latent space, tapping into users’ latent personality characteristics, and illustrating how companies can leverage the abundance of unstructured data in social media, our paper provides actionable insights regarding the future potential of social media advertising and advanced microtargeting based on big data and deep learning.The online appendix is available at https://doi.org/10.1287/isre.2017.0768 .
- 1 September 2018
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 29 (3) , 612-640
Top Cited PapersThe Impact of User Personality Traits on Word of Mouth: Text-Mining Social Media Platforms
Word of mouth (WOM) plays an increasingly important role in shaping consumers’ behavior and preferences. In this paper, we examine whether latent personality traits of online users accentuate or attenuate the effectiveness of WOM in social media platforms. To answer this question, we leverage machine-learning methods in combination with econometric techniques utilizing a novel quasi-experiment. Our analysis yields two main results. First, there is a positive and statistically significant effect of the level of personality similarity between two social media users on the likelihood of a subsequent purchase from a recipient of a WOM message after exposure to the WOM message of the sender. In particular, exposure to WOM messages from similar users in terms of personality, rather than dissimilar users, increases the likelihood of a postpurchase by 47.58%. Second, there are statistically significant effects of specific pairwise combinations of personality characteristics of senders and recipients of WOM messages on the effectiveness of WOM. For instance, introverted users are responsive to WOM, in contrast to extroverted users. Besides this, agreeable, conscientious, and open social media users are more effective disseminators of WOM. In addition, WOM originating from users with low levels of emotional range affects similar users, whereas for high levels of emotional range, increased similarity usually has the opposite effect. The examined effects are also of significant economic importance, as, for instance, a WOM message from an extrovert user to an introvert peer increases the likelihood of a subsequent purchase by 71.28%. Our findings are robust to several alternative methods and specifications, such as controlling for latent user homophily and network structure roles based on deep-learning models. By extending the characteristics that have been theorized to affect the effectiveness of WOM from the observable to the latent space, tapping into users’ latent personality characteristics, and illustrating how companies can leverage the abundance of unstructured data in social media, our paper provides actionable insights regarding the future potential of social media advertising and advanced microtargeting based on big data and deep learning.The online appendix is available at https://doi.org/10.1287/isre.2017.0768 .
- Open Access
- 23 October 2015
- Published by Elsevier in SSRN Electronic Journal
Estimating the Impact of User Personality Traits on Word-of-Mouth: Text-Mining Microblogging Platforms
Word-of-mouth (WOM) plays an increasingly important role in shaping consumers’ behavior and preferences as users’ opinions and choices are frequently shared in social media. In this paper, we examine whether latent personality traits of online users accentuate or attenuate the effectiveness of WOM in microblogging platforms. To answer this question, we leverage data-mining and machine-learning methods in combination with econometric techniques utilizing a novel quasi-experiment. Our analysis yields two main results. First, there is a positive and statistically significant effect of the level of personality similarity between two social media users on the likelihood of a subsequent purchase from a recipient of a WOM message after exposure to the WOM message of the sender. In particular, exposure to WOM messages from similar users in terms of personality, rather than dissimilar users, increases the likelihood of a post-purchase by 47.58%. Second, there are statistically significant effects of specific pairwise combinations of personality characteristics of senders and recipients of WOM messages on the effectiveness of WOM. For instance, introvert users are responsive to WOM, in contrast to extrovert users. Besides, agreeable, conscientious, and open social media users are more effective disseminators of WOM. In addition, WOM originating from users with low levels of emotional range affects similar users whereas for high levels of emotional range increased similarity has usually the opposite effect. The examined effects are also of significant economic importance as, for instance, a WOM message from an extrovert user to an introvert peer increases the likelihood of a subsequent purchase by 71.28%. Our findings are robust to several alternative methods and specifications, such as controlling for latent user homophily and network structure roles based on deep-learning models. By extending the characteristics that have been theorized to affect the effectiveness of WOM from the observable to the latent space, tapping into users’ latent personality characteristics, and illustrating how companies can leverage the abundance of unstructured data in social media, our paper provides actionable insights regarding the future potential of social media advertising and advanced micro-targeting based on big data and deep learning.
- 23 October 2015
- Published by Elsevier in SSRN Electronic Journal
Open AccessEstimating the Impact of User Personality Traits on Word-of-Mouth: Text-Mining Microblogging Platforms
Word-of-mouth (WOM) plays an increasingly important role in shaping consumers’ behavior and preferences as users’ opinions and choices are frequently shared in social media. In this paper, we examine whether latent personality traits of online users accentuate or attenuate the effectiveness of WOM in microblogging platforms. To answer this question, we leverage data-mining and machine-learning methods in combination with econometric techniques utilizing a novel quasi-experiment. Our analysis yields two main results. First, there is a positive and statistically significant effect of the level of personality similarity between two social media users on the likelihood of a subsequent purchase from a recipient of a WOM message after exposure to the WOM message of the sender. In particular, exposure to WOM messages from similar users in terms of personality, rather than dissimilar users, increases the likelihood of a post-purchase by 47.58%. Second, there are statistically significant effects of specific pairwise combinations of personality characteristics of senders and recipients of WOM messages on the effectiveness of WOM. For instance, introvert users are responsive to WOM, in contrast to extrovert users. Besides, agreeable, conscientious, and open social media users are more effective disseminators of WOM. In addition, WOM originating from users with low levels of emotional range affects similar users whereas for high levels of emotional range increased similarity has usually the opposite effect. The examined effects are also of significant economic importance as, for instance, a WOM message from an extrovert user to an introvert peer increases the likelihood of a subsequent purchase by 71.28%. Our findings are robust to several alternative methods and specifications, such as controlling for latent user homophily and network structure roles based on deep-learning models. By extending the characteristics that have been theorized to affect the effectiveness of WOM from the observable to the latent space, tapping into users’ latent personality characteristics, and illustrating how companies can leverage the abundance of unstructured data in social media, our paper provides actionable insights regarding the future potential of social media advertising and advanced micro-targeting based on big data and deep learning.
- Open Access
- 10 August 2015
- Published by Association for Computing Machinery (ACM)
- p. 1641-1650
The Effectiveness of Marketing Strategies in Social Media
This paper studies a novel social media venture and seeks to understand the effectiveness of marketing strategies in social media platforms by evaluating their impact on participating brands and organizations. We use a real-world data set and employ a promising research approach combining econometric with predictive modeling techniques in a causal estimation framework that allows for more accurate counterfactuals. Based on the results of the presented analysis and focusing on the long-term business value of marketing strategies in social media, we find that promotional events leveraging implicit or explicit advocacy in social media platforms result in significant abnormal returns for the participating brand, in terms of expanding the social media fan base of the firm. The effect is also economically significant as it corresponds to an increase of several thousand additional new followers per day for an average size brand. We also precisely quantify the impact of various promotion characteristics and demonstrate what types of promotions are more effective and for which brands, while suggesting specific tactical strategies. For instance, despite the competition for consumers' attention, brands and marketers should broadcast marketing messages on social networks during the time of peak usage in order to maximize their returns. Overall, we provide actionable insights with major implications for firms and social media platforms and contribute to the related literature as we discover new rich findings enabled by the employed causal estimation framework.
- 10 August 2015
- Published by Association for Computing Machinery (ACM)
- p. 1641-1650
Open AccessThe Effectiveness of Marketing Strategies in Social Media
This paper studies a novel social media venture and seeks to understand the effectiveness of marketing strategies in social media platforms by evaluating their impact on participating brands and organizations. We use a real-world data set and employ a promising research approach combining econometric with predictive modeling techniques in a causal estimation framework that allows for more accurate counterfactuals. Based on the results of the presented analysis and focusing on the long-term business value of marketing strategies in social media, we find that promotional events leveraging implicit or explicit advocacy in social media platforms result in significant abnormal returns for the participating brand, in terms of expanding the social media fan base of the firm. The effect is also economically significant as it corresponds to an increase of several thousand additional new followers per day for an average size brand. We also precisely quantify the impact of various promotion characteristics and demonstrate what types of promotions are more effective and for which brands, while suggesting specific tactical strategies. For instance, despite the competition for consumers' attention, brands and marketers should broadcast marketing messages on social networks during the time of peak usage in order to maximize their returns. Overall, we provide actionable insights with major implications for firms and social media platforms and contribute to the related literature as we discover new rich findings enabled by the employed causal estimation framework.