Reducing inferior member community participation using uplift modeling: Evidence from a field experiment

Abstract

In their ongoing search for competitive advantage, firms increasingly leverage online innovation communities (ICs). The viability of these ICs may be jeopardized by big data environments and inferior member participation. Therefore, community managers must address poor member participation, together with the data-rich environment. This study examines the viability of a proactive motivational email campaign to reduce inferior member participation using uplift modeling; it also explores optimal treatment characteristics, including message scope (untargeted versus targeted), message content (hedonic, cognitive, and social message), and member profile (self-interest-oriented and positive emotional writing style). The findings indicate that marketing decision makers should use proactive, targeted emails with cognitive motivational elements to mitigate inferior levels of member participation. These findings have important implications for innovation scholars and community managers.

Continuous idea contribution in open innovation communities: The role of verbal persuasion from peers

“…To construct the linguistic style variables representing the dimensions of verbal persuasion, we utilize the Linguistic Inquiry and Word Count (LIWC) ( Zhou et al, 2012 ), an automated text analysis tool that supports analyses of how members’ comments are written ( Debaere et al, 2019 ). Based on the pre-categorized dictionary, this approach assesses each comment and assigns a final score according to the percentage of words that belong to a certain word category.…”

“…Previous literature in online communities have identified various influencing factors of participants’ contribution behavior, including enjoyment ( Wasko and Faraj, 2005 ), expertise ( Zhu et al, 2017 ), self-image ( Chen et al, 2018 ) and reputation ( Liao et al, 2013 ), etc. In general, members contribute if they expect to receive future benefits ( Debaere et al, 2019 ). However, the antecedents of continuous and initial contribution may be varied, since factors emerging after the first instance may impact the decision to remain engaged ( Zhang et al, 2013 ).…”

To Impute or not to Impute? Missing Data in Treatment Effect Estimation

“…Treatment effect models are adopted in a wide range of fields such as: medicine [8,9,10,11,12], marketing [13,14,15], and even human resources [16]. However, these methods have almost exclusively assumed that data is complete.…”