Beyond Human Touch: LLM-Driven Automatic Responses to Customer Reviews (Ref: RDF24/EE/CIS/LI)

In the era of e-commerce and digital brand interactions, customer reviews stand as a potent touchpoint, influencing both prospective customers and brand reputation. As customer expectations evolve, the timeliness and appropriateness of managerial responses to these reviews have become paramount in fostering loyalty and ensuring repeat purchase. While many companies manually address customer reviews, the demand for speed, scalability and consistency points towards the need for an automated system.

While there exists extensive literature on customer satisfaction and the impact of managerial response on loyalty, there is limited investigation of automatic response systems, especially those integrating cutting-edge technologies like Large Language Models (LLMs). Current research primarily focuss on the content of managerial responses without delving deep into automation or the potential of AI in crafting these responses. Moreover, the potential of LLMs, like GPT variants, in understanding customer sentiment and generating contextually relevant feedback has not been thoroughly examined in the context of customer review response systems.

This research project aims to bridge the existing literature gaps by developing an automatic response generation system underpinned by LLMs. The objectives of the project are:

1. Investigating the crucial components that a managerial response should encompass to encourage customer retention and repeat purchases. This will involve a rigorous literature review, primary research methodologies (such as surveys or interviews) and secondary data analysis.
2. Incorporating the above components into LLMs, by fine-tuning existing models using an annotated dataset of customer reivews and associated managerial responses. The goal is to align the LLM’s output with the identified factors that resonate most with customers.
3. Developing a system that automatically generates responses integrating the identified factors using the trained LLMs.

The proposed system promises not only scalability but also consistency in response quality, addressing both the volume and variability challenges associated with manual responses. Anticipated results include the development of a highly efficient LLM-based system capable of generating managerial responses that resonate with customers, leading to enhanced satisfaction and loyalty. Comparative analsysis with human-crafted responses and generic LLM responses might reveal the superior effectiveness of the fine-tuned model in specific contexts. Furthermore, the system’s scalability could potentially address response delays, one of the critical pain points in customer feedback mechanisms.

The potential contribution of this project is three-fold. First, this project exemplifies the integration of theoretical research and existing knowledge into the practical application and fine-tuning of LLMs. By doing so, it addresses the notable absence in literature concerning the union of theoretical insights with AI-driven automation for feedback mechanisms. This fusion of theory and technology not only champions the adaptability of LLMs but also lays the foundation for future research that marries theoretical frameworks with advanced AI applications. Secondly, on the business front, by facilitating timely, contextually apt, and consistent communication, this project equips both enterprises and SMEs with an invaluable tool, potentially bolstering brand loyalty and profit margins. This offers a pragmatic solution to the challenges of manual responses previously highlighted. Lastly, it examines the dynamics between LLMs and variaed customer feedback, setting a precedent for future studies on AI-driven customer engagement mechanisms.

Academic Enquiries

This project is supervised by Dr. Yulei Li. For informal queries, please contact [Email Address Removed]. For all other enquiries relating to eligibility or application process please contact Admissions at [Email Address Removed]. 

Eligibility Requirements:

• Academic excellence i.e. 2:1 (or equivalent GPA from non-UK universities with preference for 1st class honours); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.
• Applicants cannot apply if they are already a PhD or Professional Doctorate holder or if currently engaged in Doctoral study at Northumbria or elsewhere.

To be classed as a Home student, candidates must:

• Be a UK National (meeting residency requirements), or
• have settled status, or
• have pre-settled status (meeting residency requirements), or
• have indefinite leave to remain or enter.

If a candidate does not meet the criteria above, they would be classed as an International student. 

Applicants must be fully enrolled in the UK before stipend payments can commence and cover any additional costs that may be incurred, as these are not covered by the studentship:

• Immigration Health Surcharge https://www.gov.uk/healthcare-immigration-application
• If you need to apply for a Student Visa to enter the UK, please refer to https://www.gov.uk/student-visa. It is important that you read this information carefully as it is your responsibility to ensure that you hold the correct funds required for your visa application, otherwise your visa may be refused.
• Costs associated with English Language requirements which may be required for students not having completed a first degree in English, will not be paid by the University.

APPLY HERE:

https://www.northumbria.ac.uk/research/postgraduate-research-degrees/how-to-apply/  

In your application, please include a research proposal of approximately 1,000 words and the advert reference (e.g. RDF24/…).

Deadline for applications: 26 January 2024

Start date of course: 1 October 2024

Northumbria University is committed to creating an inclusive culture where we take pride in, and value, the diversity of our postgraduate research students. We encourage and welcome applications from all members of the community. The University holds a bronze Athena Swan award in recognition of our commitment to advancing gender equality, we are a Disability Confident Leader, a member of the Race Equality Charter and are participating in the Stonewall Diversity Champion Programme. We also hold the HR Excellence in Research award for implementing the concordat supporting the career Development of Researchers and are members of the Euraxess initiative to deliver information and support to professional researchers.