This thesis explores the intersection between the marketing literature and Natural Language Processing. From a methodological perspective, NLP has provided marketing scholars with new metrics and tools, like sentiment analysis and topic modelling, that enabled them to analyze textual data more in-depth and on a larger scale. One of the research areas most affected by these methodological advancements is research on Online Word Of Mouth and social media interactions in general. Within this field, we generally observe two types of research that use NLP methods: studies on the effect of social media interaction on external phenomena, like company performance, and studies about the interaction among the online actors. The three essays of this thesis follow this three folded classification (methodology, performance and online dynamics). In the first one, "The Telephone Game: the effect of online communication similarity on market performance", we study the effect of semantic similarity on market performance. Semantic similarity has been so far neglected in marketing to our knowledge. However, we argue that it is an important dimension of online communication dynamics since it can measure how much of the original brand message gets retained in consumers’ communication. This information helps consumers evaluate their fit with the brand, and hence it contributes to the effect of online communication on market performance. We find that semantic similarity positively affects market performance. The second essay, "Culture of Innovation: A Comprehensive Literature Review Using Natural Language Processing", is intended to provide a methodological contribution. We argue that, although there is no ready-to-use algorithm for literature reviews, different NLP methods can be used to assist researchers during the literature review process. Hence we try to apply them to review the literature about the culture of innovation. Finally, the third essay, "Disentangling the "echoverse" for brand communication", is a research proposal about social media dynamics between brands and consumers. The tendency of consumers to diverge from brand content creates a constant tension for brands between the need to keep up with its consumers to keep them engaged and the need to keep control of its own narrative. To assess how the conversational content between brands and consumers changes over time and who drives the change, we will observe the shifts in topics discussed by brands and consumers across ten years of Twitter data.

NLP methods to inform Marketing Strategy

PUGLIESE, SERENA
2022

Abstract

This thesis explores the intersection between the marketing literature and Natural Language Processing. From a methodological perspective, NLP has provided marketing scholars with new metrics and tools, like sentiment analysis and topic modelling, that enabled them to analyze textual data more in-depth and on a larger scale. One of the research areas most affected by these methodological advancements is research on Online Word Of Mouth and social media interactions in general. Within this field, we generally observe two types of research that use NLP methods: studies on the effect of social media interaction on external phenomena, like company performance, and studies about the interaction among the online actors. The three essays of this thesis follow this three folded classification (methodology, performance and online dynamics). In the first one, "The Telephone Game: the effect of online communication similarity on market performance", we study the effect of semantic similarity on market performance. Semantic similarity has been so far neglected in marketing to our knowledge. However, we argue that it is an important dimension of online communication dynamics since it can measure how much of the original brand message gets retained in consumers’ communication. This information helps consumers evaluate their fit with the brand, and hence it contributes to the effect of online communication on market performance. We find that semantic similarity positively affects market performance. The second essay, "Culture of Innovation: A Comprehensive Literature Review Using Natural Language Processing", is intended to provide a methodological contribution. We argue that, although there is no ready-to-use algorithm for literature reviews, different NLP methods can be used to assist researchers during the literature review process. Hence we try to apply them to review the literature about the culture of innovation. Finally, the third essay, "Disentangling the "echoverse" for brand communication", is a research proposal about social media dynamics between brands and consumers. The tendency of consumers to diverge from brand content creates a constant tension for brands between the need to keep up with its consumers to keep them engaged and the need to keep control of its own narrative. To assess how the conversational content between brands and consumers changes over time and who drives the change, we will observe the shifts in topics discussed by brands and consumers across ten years of Twitter data.
28-giu-2022
Inglese
33
2020/2021
BUSINESS ADMINISTRATION AND MANAGEMENT
Settore SECS-P/08 - Economia e Gestione delle Imprese
HOVY, DIRK
RUBERA, GAIA
File in questo prodotto:
File Dimensione Formato  
Thesis_SerenaPugliese.pdf

accesso aperto

Descrizione: Thesis_SerenaPugliese
Tipologia: Tesi di dottorato
Dimensione 1.79 MB
Formato Adobe PDF
1.79 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11565/4058572
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact