Organisations which sell services or products to mass audiences struggle to understand the reasons why their customers are happy, and especially how the preferences evolve over time. The problem of understanding reasons for customer satisfaction over time stems from methodological difficulty in analysing written customer reviews as time series data. This project trials use of sentiment analysis to understand evolution of feedback over time. Sentiment models trained using Recurrent Neural Network, Naive Bayes and Maximum Entropy are compared and the best model is selected to predict feedback in the future. Difference in predictive accuracy over time is assessed for the selected model. Moreover, visuals are developed to depict how text features and themes vary in importance when it comes to accurate prediction of satisfaction over time. The objective is to enable real-time visualization and understanding of patterns in customer feedback over time from big text corpora

Mattio argues that in the last few years laws have increasingly become a preferred and often unquestioned means of attempting to enforce human rights. The use of human rights to mandate expanded penalty (intended as the entire “penal field”, including its laws, sanctions, institutions, practices, discourses, and representations) is mostly to be seen in the recent developments of international criminal law and transitional justice, but the phenomenon is also emerging within domestic criminal law (Teitel 2003; Tulken 2011). This paradigmatic shift raises several questions and needs to be examined further. Through the case-study of human trafficking and sexual violence and drawing on discourse analysis and socio-legal theory, the project will investigate legal and discursive practices of domestic and international tribunals, NGOs and policy-makers in order to understand how and why they are increasingly justifying the application of criminal measures by reference to human rights, and what the effects of this tendency might be.

Prostate cancer is a very heterogeneous disease with variable molecular phenotypes and clinical outcomes. The challenges and clinical unmet needs are to understand how the tumor evolves and effectively track the disease change along the treatment. Circulating cell-free DNA (ccfDNA) in plasma is fragmented DNA present in our circulation and analysis of plasma DNA occurs as an emerging clinical opportunity to enable us to trace tumor changes, and identify signatures associated with the outcomes. While most current plasma DNA analyses focus on genomic aberrations, DNA methylation is shown to be a stable, easily-quantifiable biomarker that is tissue-specific. My project is to profile methylome from low-input ccfDNA in plasma and our initial data indicates DNA methylation signatures extracted from plasma DNA could accurately estimates tumor fraction changes before and after treatments such as AR-targeting agent abiraterone or docetaxel.

For Inquisitive Minds is a fortnightly podcast showcasing post graduate work in all areas. The podcast seeks to identify ground breaking research and bring it to the masses. Visit patreon.com/forinquisitiveminds to learn more about our work!

TBD

Keegan explores ambulance settings are incredibly under-researched when compared to that of hospitals and primary care settings, and so it's very exploratory and aiming to capture perceptions of staff in regards to how they view patient safety in general, the reporting of incidents, organisational culture, etc. 

For Inquisitive Minds is a fortnightly podcast showcasing post graduate work in all areas. The podcast seeks to identify ground breaking research and bring it to the masses. Visit patreon.com/forinquisitiveminds to learn more about our work!

Davide is a PhD student at University College London, studying how machine learning could be applied to replicate simulations of our Universe. His main research thus focus on Astrophysics and generative algorithms, even though he published a paper on intrinsic alignment a couple of years ago.

To learn more about him, you can visit his LinkedIn profile, or you can directly tell him why you disagree with his views by dropping him a few lines at [email protected].

For Inquisitive Minds is a fortnightly podcast showcasing post graduate work in all areas. The podcast seeks to identify ground breaking research and bring it to the masses. Visit patreon.com/forinquisitiveminds to learn more about our work!

Rhianna works at Imperial College London, raising funds for research within Medicine and Sciences. She also conducts research into Neglected Tropical Diseases, such as Schistosomiasis. This study examines ecological theory and sustainable intervention methods, using the Senegal River in Uganda as a lens. You can reach her via LinkedIn; https://www.linkedin.com/in/rhianna-patricia-williams/ 

For Inquisitive Minds is a fortnightly podcast showcasing post graduate work in all areas. The podcast seeks to identify ground breaking research and bring it to the masses. Visit patreon.com/forinquisitiveminds to learn more about our work!

Rafah did her PhD in Coding Theory at EPFL, Switzerland and is now a data scientist at ING in London. Her research focused on the analysis of an optimisation algorithm, called belief propagation, that is used in telecommunications and machine learning, among other fields, using notions from functional analysis. Her conference and journal papers can be found here: https://arxiv.org/search/?searchtype=author&query=El-Khatib%2C+R

For Inquisitive Minds is a fortnightly podcast showcasing post graduate work in all areas. The podcast seeks to identify ground breaking research and bring it to the masses. Visit patreon.com/forinquisitiveminds to learn more about our work!

Will Bowers is a PhD researcher at the institute of Cancer Research. He is focusing on defining biomarkers of tyrosine kinase inhibitor response in soft tissue sarcoma. To break that down, soft tissue sarcoma (STS) is a rare cancer category (<1% of all cancers) which skews more towards young people. Receptor tyrosine kinase inhibitors (RTKIs) are a common drug used in chemotherapy, though some cancer types become resistant. By analysing blood samples and tumor biopsies, we can computationally assess how different patients respond to the drugs, then we can then predict which patients will have the best response in the future.

For Inquisitive Minds is a fortnightly podcast showcasing post graduate work in all areas. The podcast seeks to identify ground breaking research and bring it to the masses. Visit patreon.com/forinquisitiveminds to learn more about our work!