For best experience please turn on javascript and use a modern browser!
uva.nl

Kedma Hamelberg

Introduction

Kedma Hamelberg is a PhD candidate in the Marketing department since September 2021. Her research project investigates that since the urgency of making our world a better place is growing exponentially, responsible marketing is rising as one of the most relevant forces to voice and positively influence customer behaviour and public opinion. With society switching gears towards digital communication, responsible marketing pays extra attention to how online activities shape society at different levels. Thus, the broader goal of this research is to apply cutting edge methodologies (e.g. NLP, Deep Learning) to investigate the responsible use of unstructured (text) data in marketing-customer analytics.

More specifically, it involves the following projects:
1. The first project aims to classify the different social media speakers (entities) and test how society perceives each characteristic from speakers and content (e.g. framing of responsibility) individually and synergistically. Also, it investigates the network dynamics of engagement in the online green debate.

2. What drives prosocial behaviour? By examining online social crowdfunding data of targeted (i.e. online platforms) and non-targeted audiences (i.e. social media), the second project intent to uncover the motivations of online donations and how the different elements in the text, type of cause (e.g. environment, health) influence donation performance.

3. "How can I help you?" Although it is a simple question, the answer style (i.e. what they say and how they say it) can reveal fundamental aspects of customer identity and personality to improve customer service. Thus, the third project examines how
the early detection of hidden elements of customer identity inferred from their answer' syntax and semantics (e.g. topics, conciseness, and sentiments) can improve online customer service in Chatbot.

4. The fourth project collaborates with a Dutch corporation and investigates how customers express their feelings-topics in different settings and how it affects service outcomes (e.g. problem resolution, helpfulness). For example, what drives consumers media choice? How do public (i.e. open post on social media) and private communication environments (e.g. closed chat with the company via their website) affect consumers' perception of service quality? The settings to be analysed are:
• Human-to-Human (voice communication) – speech to text call centre data 
• Human-to-Machine (voice communication) – speech to text call centre data (with VRS system)
• Human-to-Human (online live chat and via social media)
• Human-to-Machine (online chat with a Chatbot and via social media)