FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Exploring the challenges and opportunities of Natural Language Processing (NLP) in Social Media Analytics within healthcare

   Faculty of Engineering and Informatics

  Dr Kulvinder Panesar,  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Social media analytics, as described by techopaedia (2021) is the approach of collecting data from social media networking sites such as Facebook, Twitter, WhatsApp, Medium and WeChat, and blogs such as Slack and HubSpot. Conducting various analyses and evaluations for decision making, are increasingly used in the healthcare domain.   

This data is multi-form and largely text based written in natural language (NL) to serve several purposes such as answering NL questions, topic modelling, collaborative filtering and recommender systems, text classification/summarisation, sentiment analysis, parsing and machine translation. The task of processing NL is known as Natural Language Processing (NLP) - a theory motivated range of computational techniques for analysing and representing natural occurring texts at one or more levels of linguistic analysis for the purpose of achieving human-like language processing for a range of tasks or application’(Liddy, 2001) (Young et al., 2018). Human language is symbolic (based on logic, rules, and ontologies), discrete and highly ambiguous. In the  example Tweet “ there is little awareness or understanding about feelings of grief and bereavement when a person is still living, but when you care for someone with dementia, loss does not just mean loss of life” ("", 2021). This demonstrates high variability, whereby the core message is  living grief and bereavement. This type of  variability has called for a statistical machine learning approach for NLP (Goldberg, 2017). Additionally, the nuances of meaning make natural language understanding (NLU) difficult as the text’s meaning can be influenced by context and reader’s “world view” (Sharda et al., 2019).  

The year 2020, was defined by uncertainty and the global pandemic, witnessed increased investment into innovation and AI adoption, and has brought the future forward by 5 years, evidently at the forefront across business units (Muehmel, 2020). Deep learning architecture and algorithms have demonstrated impressive advances in computer vision and pattern recognition. This trend has followed in the NLP space, moving from machine learning NLP problems of shallow models (e.g., SVM and logistic regression) trained on very high dimensional and sparse features to neural networks based on low dimensional, dense and distributed representations as deep new language models and demonstrating superior results in the NLP landscape (Young et al., 2018) (Omarsar, 2018).

There are a range of challenges and opportunities  of social analytics with innovative NLP approaches. For example, social media analytics and sentiment analysis on dialogue about Covid vs Flu vaccines  - may provide an indication of the  the mood of people and insight to senior decision makers and technical professionals, but contentious due to the accuracy and precision     

This project aims to design and develop a range of NLP hybrid (Saba, 2020a, Saba, 2020b, Mcshane and Nirenburg, 2021, Ball, 2019, Ball, 2021) – linguistic and machine learning experimental solutions in a specific healthcare theme, focusing on NLU understanding, high evaluation benchmarks and validation outcomes This research project will sit in our AI and Visual Computing Research Unit, part of the AI Research group ("universityofbradford", 2021). Here we have a  small research group in NLP who has published work on the motivations, design and evaluation of conversational agents and is part of a globally established NLP, and knowledge representation community.

This research project will serve as a blueprint framework  for a  hybrid NLP driven social media analytics for healthcare. The research project will have much impact in healthcare – in terms of more sophisticated approaches to social media analytics for decision making from a patient to a strategic level. One use case  is dementia ("", 2020) and the use of social media by patients offering a  unique set of challenges and opportunities and responses by the community, and impact on holistic patient care.    

Applicants with a background in computer science, natural language processing and an interest in language itself are welcome to apply, particularly with expertise in any of the following programming languages (Python, Java, C, C++, or C#), and an interest in human computer interaction and integration development are welcome. The domain of this project can be adjusted as per the qualification and interests of students.

Funding Notes

This is a self-funded PhD project; applicants will be expected to pay their own fees or have a suitable source of third-party funding. UK students may be able to apply for a Doctoral Loan from Student Finance for financial support.


"NHS.UK". 2020. About Dementia [Online]. NHS. Available: [Accessed 10th December 2020].
"TECHOPAEDIA! 2021. What Does Social Media Analytics (SMA) Mean? [Online]. Available: [Accessed].
"TWITTER.COM". 2021. Living Grief & Bereavement event #DCAN @DementiaCan [Online]. Available from:
"UNIVERSITYOFBRADFORD". 2021. AI and Visual Computing Research Unit [Online]. Available: [Accessed].
BALL, J. 2019. The Problem with AI State of the Art Methodology [Online]. Pat Inc. Available: [Accessed 1 June 2019].
BALL, J. 2021. Using Meaning as Universal Knowledge Representation [Online]. "Pat.Inc". Available: [Accessed 2 Mar 2021].
GOLDBERG, Y. 2017. Neural network methods for natural language processing. Synthesis lectures on human language technologies, 10, 1-309.
LIDDY, E. D. 2001. Natural language processing. Encyclopedia of Library and Information Science. NY: Marcel Decker, Inc.
MCSHANE, M. & NIRENBURG, S. 2021. Linguistics for the Age of AI, MIT Press.
MUEHMEL, K. 2020. AI Projects Get to Down to Business in 2020 [Online]. "". Available: [Accessed 12 December 2020].
OMARSAR, E. 2018. Deep Learning for NLP: An Overview of Recent Trends [Online]. Available: [Accessed 1 May 2019].
SABA, W. 2020a. Time to put an end to BERTology (or, ML/DL is not even relevant to NLU) [Online]. Available: [Accessed 4 Dec 2020].
SABA, W. 2020b. Why Ambiguity is Necessary, and why Natural Language is not Learnable [Online]. Available: [Accessed].
SHARDA, R., DELEN, D. & TURBAN, E. 2019. Analytics, Data Science, & Artificial Intelligence: Systems for Decision Support, Pearson.
YOUNG, T., HAZARIKA, D., PORIA, S. & CAMBRIA, E. 2018. Recent trends in deep learning based natural language processing. ieee Computational intelligenCe magazine, 13, 55-75.

Email Now

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs