Abstract
Network Effects and Social Sentiment: The Influence of Electronic Word-of-Mouth on Sales Author: Kun-Ting Pai Advisor: Dr. Jyun-Cheng Wang Abstract Electronic word-of-mouth (eWOM) from online social media has become increasingly important in influencing customers’ purchasing decisions. More and more firms are taking advantage of eWOM as a new marketing tool, which can collect social intelligence data over different platform content. This study uses the data from the online mobile community as well as actual sales data to analyze the impact of topic, response, social network indicators, and eWOM entropy to determine eWOM generation in relation to product sales. The results show that the topic of eWOM has a positive impact on product sales, and the topic responses of eWOM have a positive impact on eWOM generation. In social network analysis, degree density and degree centralization have a negative impact on product sales, but betweenness centralization and the clustering coefficient have a positive impact on product sales. Degree density and degree centralization have inconsistent results in analyzing eWOM generation. Degree density has a negative impact on eWOM generation, and degree centralization has a positive impact on eWOM generation. This result also shows that the dispersion of social sentiment has both a positive impact on product sales and on eWOM generation. In practice, these results could be referenced for companies to establish future marketing strategies in social commerce. Keywords: Electronic Word-of-Mouth, Social Network Analysis, Social Sentiment Analysis