Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2366–2371 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 2366 Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success Farzana Rashid University of North Texas farzanarashid@my.unt.edu Tommaso Fornaciari Bocconi University fornaciari.tommaso@unibocconi.it Dirk Hovy Bocconi University dirk.hovy@unibocconi.it Eduardo Blanco University of North Texas eduardo.blanco@unt.edu Fernando Vega-Redondo Bocconi University fernando.vega@unibocconi.it Abstract When interacting with each other, we motivate, advise, inform, show love or power towards our peers. However, the way we interact may also hold some indication on how successful we are, as people often try to help each other to achieve their goals. We study the chat inter- actions of thousands of aspiring entrepreneurs who discuss and develop business models. We manually annotate a set of about 5,500 chat in- teractions with four dimensions of interaction styles (motivation, cooperation, equality and advice). We find that these styles can be re- liably predicted, and that the communication styles can be used to predict a number of in- dices of business success. Our findings indi- cate that successful communicators are also successful in other domains. 1 Introduction People are social beings who communicate their feelings, emotions, thoughts, ideas, etc. through verbal and non-verbal interactions. Based on these interactions, we build relationships, and these rela- tionships, in turn, help create and maintain a net- work of peers. Peers in a network cooperate with each other, help each other to learn, and exchange ideas. However, they also compete for the same re- sources (Vega-Redondo et al., 2019), not least atten- tion. Peer networks are particularly important for innovation and entrepreneurship (Gonzalez-Uribe and Leatherbee, 2017), as they produce an active exchange of ideas. People are usually assumed to be altruistic in networks like online social forums. They cooper- ate with and help one another with answers, advice, and ideas. The motivations behind helping a peer include, but are not limited to, getting pure plea- sure from helping, self-advancement, building a reputation, developing relationships, or sheer enter- tainment (Tausczik and Pennebaker, 2012). When people interact with each other, their inter- actions vary along various communicative styles, such as showing cooperativeness, equality, busi- ness orientation, etc. (Rashid and Blanco, 2018). Varying these communication styles provides tools to achieve communicative goals. For example, someone trying to build a reputation will tend to use a more cooperative style. Someone who tries to be helpful may use more words of advice in their interactions. The usage of relationship- establishing styles is more prevalent in certain per- sonalities (Cheng, 2011) and in specific settings. Business-oriented people communicate more in- dependence, tolerance of ambiguity, risk-taking propensity, innovativeness, and leadership quali- ties (Wagener et al., 2010). The impact of these styles is, therefore, an essen- tial factor in text analysis. However, due to their complex, decentralized nature, these communica- tion styles have been studied very little in NLP. Cooperativeness is more than just a few keywords— it includes a whole inventory of communicative tools. This property …

Content truncated to 500 words