profile image

Dr Lowri Williams

Research Data Scientist at Cardiff University

About Me

A research data scientist with 4 years of experience in academic research and 2 years in industry-based collaborations supporting small-medium businesses with novel data science solutions.

Research areas and interests: natural language processing, computational linguistics, data mining, text mining, sentiment analysis, language resources, machine learning, feature engineering, classification, classification schemes, data science, data annotation, crowdsourcing.

Collaborated with multidisciplinary experts, as well as applying expertise within different academic disciplines such as cybersecurity, to present research outputs and findings within several reputable academic journals. This shows creativity within my research by using state of the art technologies to tackle complex research problems.

Personal Projects and Blogs


WordNet: A Lexical Taxonomy of English Words

26/01/2021

What is WordNet and why is it useful?

Read here

Python Natural Language Processing WordNet NLTK

Portal COVID-19 Cymru

24/12/2020

The purpose of this portal is to report and share Welsh COVID-19 data and statistics from different sources.

See here

Python Data Science HTML CSS Javascript

Sentiment Analysis: Aspect-Based Opinion Mining

27/10/2020

An investigation into sentiment analysis and topic modelling techniques.

Read here

Python Data Science Machine Learning Natural Language Processing Sentiment Analysis
project name

Sentiment Analysis: Idioms and their Importance

23/09/2020

An investigation into the role of idioms in sentiment analysis.

Read here

Python Data Science Machine Learning Natural Language Processing Sentiment Analysis

Coronavirus: Mapping COVID-19 Daily Cases in Wales

01/09/2020

Mapping the number of COVID-19 cases in Wales using a heat map.

See here

Python Data Science Data Visualisation
project name

Adversarial Attacks on SMS Spam Detectors

19/08/2020

Exploring how adversarial learning can be used to target SMS spam detectors using Jacobian-based Saliency Map attacks.

Read here

Python Data Science Machine Learning Adverserial Machine Learning Natural Language Processing Word Embeddings
project name

Coronavirus: Using Machine Learning to Triage COVID-19 Patients

31/07/2020

Analysing and classifying real patient cough sounds.

Read here

Python Data Science Machine Learning Audio Analysis Image Analysis
project name

Topic Modelling: Going Beyond Token Outputs

16/07/2020

An investigation into how to assign topics with meaningful titles.

Read here

Python Data Science Natural Language Processing Topic Modelling Keyword Extraction
project name

Predicting the Scores of the Postponed 2020 Rugby Six Nations Matches

14/06/2020

An analysis on Rugby Six Nations data.

Read here

Python Pandas Data Science Regression
project name

Spotify Sentiment Analysis

20/05/2020

A sentiment analysis project on Spotify data.

Read here

Python Pandas Data Science Natural Language Processing Sentiment Analysis
project name

Coronavirus: A Data Scientist’s Perspective

05/04/2020

An analysis on the coronavirus data.

Read here

Python Pandas Data Science

Publications

  A Three-Tiered Intrusion Detection System for Industrial Control Systems (ICS).
         E Anthi, L Williams, P Burnap, K Jones.
         Journal of Cybersecurity, Volume 7, Issue 1, 2021.


  Adversarial Attacks on Machine Learning Cybersecurity Defences in Industrial Control Systems.
         E Anthi, L Williams, M Rhode, P Burnap, A Wedgbury.
         Journal of Information Security and Applications, Volume 58, 102717, 2021.


  Comparing the Utility of Different Classification Schemes for Emotive Language Analysis.
         L Williams, M Arribas-Ayllon, A Artemiou, I Spasić.
         Journal of Classification 36 (3), 619-648. 2019.


  A Supervised Intrusion Detection System for Smart Home IoT Devices.
         E Anthi, L Williams, M Słowińska, G Theodorakopoulos, P Burnap.
         IEEE Internet of Things Journal 6 (5), 9042-9053. 2019.


  Pulse: An Adaptive Intrusion Detection for the Internet of Things.
         E Anthi, L Williams, P Burnap.
         Living in the Internet of Things: Cybersecurity of the IoT-2018 (pp. 1-4). IET. 2018.


  Idiom Based Features in Sentiment Analysis: Cutting the Gordian Knot.
         I Spasić, L Williams, A Buerki.
         IEEE Transactions on Affective Computing 11 (2), 189-199. 2017.


  Pushing the Envelope of Sentiment Analysis Beyond Words and Polarities.
         L Williams.
         PhD Thesis. Cardiff University. 2017.


  The Role of Idioms in Sentiment Analysis.
         L Williams, C Bannister, M Arribas-Ayllon, A Preece, I Spasić.
         Expert Systems with Applications 42 (21), 7375-7385. 2015.