Victoria Sherratt  ·  Manchester, UK

I build AI systems, and research how meaning works inside them.

Six years as co-founder and Director of Data Science of a data consultancy serving over 40 UK higher-education institutions, owning the technical agenda and developing agentic AI pipelines and bespoke analytical products. Alongside that, a PhD in computer science developing symbolic and subsymbolic methods for multimodal understanding, with six first-author publications and an openly released knowledge graph dataset.

victoria@vsherratt.com ORCID 0000-0002-6366-8310

What I do

Consultancy

Technical strategy, analytical methodology, infrastructure and data governance for organisations working with large-scale data. Designing agentic pipelines, production AI systems, and developing technical teams. My industry work focuses on turning current research into deployed applications and developing solutions for complex problems that non-technical stakeholders can act on.

Research

Multimodal machine learning and vision-language models; knowledge graphs and neuro-symbolic AI; computational semantics and pragmatics. My work operationalises semiotic theory computationally, modelling how meaning is constructed, with applications in online harms, propaganda detection and content moderation.

Projects

Agentic pipeline for higher-education course data

2020–2026

An annual data cycle covering course collection, merging, subject recoding and validation across UK universities, redesigned as an agent-run workflow with staged execution and human confirmation gates. Core elements include the Model Context Protocol (MCP), tool function calling, task decomposition, multi-agent orchestration, LLM-as-judge evaluation and human-in-the-loop design.

SemioMeme — symbolic–subsymbolic knowledge graph dataset

Published at ICWSM 2026

A multimodal knowledge graph dataset for meme analysis, combining symbolic structure with learned representations. Released with a datasheet under CC-BY. doi.org/10.5281/zenodo.17826799

SemEval-2024 Task 4 — multilingual persuasion detection

Team lead, BDA (University of Hull)  ·  2024

Assembled and led a five-person research team for the shared task, coordinating the technical approach — ensemble learning with external knowledge — and delivering the published system paper at ACL.

Alan Turing Institute Enrichment Scheme

Community Award  ·  2024

A nine-month placement within the Turing's cross-disciplinary research community, with development funding.

Publications

  1. Sherratt, V., Dethlefs, N. (2026). Community-Authored Usage Glosses as Use-Conditions for Internet Memes. Proceedings of the 30th Workshop on Semantics and Pragmatics of Dialogue.Accepted
  2. Sherratt, V., Elayan, S. & Dethlefs, N. (2026). SemioMeme: A Symbolic–Subsymbolic Knowledge Graph Dataset for Multimodal Meme Analysis. Proceedings of the International AAAI Conference on Web and Social Media, 20(1), 2921–2935.Resource Paper
  3. Sherratt, V., Dethlefs, N. (2026). Clustering Internet Memes with Metric Learning and Dynamic Modality Weighting. Proceedings of the International AAAI Conference on Web and Social Media, 20(1), 2131–2148. Paper
  4. Sherratt, V., Dogan, S., Wuraola, I., Bryan-Smith, L., Onwuchekwa, O., & Dethlefs, N. (2024). BDA at SemEval-2024 Task 4: Detection of Persuasion in Memes Across Languages with Ensemble Learning and External Knowledge. Proceedings of SemEval-2024, 123–132. ACL. Paper
  5. Sherratt, V., Pimbblet, K., & Dethlefs, N. (2023). Multi-channel Convolutional Neural Network for Precise Meme Classification. Proceedings of ICMR 2023, 190–198. ACM. Paper
  6. Sherratt, V. (2022). Towards Contextually Sensitive Analysis of Memes: Meme Genealogy and Knowledge Base. Proceedings of IJCAI-22 Doctoral Consortium, 5871–5872. Paper

Experience

Co-founder & Director of Data Science

S Squared Insights Limited  ·  2020–2026

Co-founded a data analytics consultancy serving over 40 higher-education institutions, with responsibility for the company's entire technical agenda: analytical methodology, infrastructure, data strategy and governance. Built and led the data science function, recruiting and mentoring a specialised technical team to deliver large-scale insight projects. Designed and shipped production systems including agentic AI pipelines, pattern-recognition tools and bespoke analytical products.

Research Data Analyst / Student Insight Officer

University of Manchester  ·  2019–2021

Lead for data science projects in the Market and Student Insight Team, and coordinator for the introduction of machine learning to the team's remit. Projects included predictive models for student attainment and matriculation, market analysis for new course development, and competitor analysis for student recruitment strategy. As Research Data Analyst, lead developer for business analytics products relating to research strategy, REF strategy and research impact.

Researcher

Fairhome Group PLC  ·  2018–2019

Data-driven business intelligence and research briefs for external stakeholders. Lead for Geographical Information System rollout across the business, responsible for establishing GIS and building the internal GIS team.

Skills

Expertise
Large language models; agentic systems (MCP, tool function calling, task decomposition, multi-agent systems, LLM-as-judge, orchestration, human-in-the-loop design); multimodal machine learning and vision-language models; knowledge graphs and neuro-symbolic AI; evaluation and dataset design; computational semantics and pragmatics; computational social science.
Machine learning
PyTorch; multimodal ML; metric and contrastive learning; ensemble methods; embedding fine-tuning; transformer-based text and vision representations (BGE, SigLIP, CLIP-family); agentic and LLM-based systems (RAG, LangChain).
Statistical inference
Permutation-based inference (Mantel, MRQAP); multivariate controls; reproducible analysis pipelines.
Data & engineering
Python (pandas, scientific stack); R; SQL; knowledge graph construction (RDF, Neo4j); large-scale web data collection and curation; open data release (datasheets, Zenodo/CC-BY); Git/GitHub.

Education

  • PhD Computer ScienceLoughborough University
    2026
  • MSc Artificial Intelligence & Data ScienceUniversity of Hull  ·  Distinction
    2021
  • MA Contemporary Literature & Critical TheoryManchester Metropolitan University  ·  Distinction
    2018
  • BA (Hons) English & Creative WritingManchester Metropolitan University  ·  First Class
    2015

Teaching & mentoring

  • Lab Demonstrator, Loughborough UniversityFoundations for Artificial Intelligence modules, plus guest lectures.
    2026
  • Team Lead, SemEval-2024 Shared Task (BDA)University of Hull. Led a five-person research team to a published ACL system paper.
    2024
  • Graduate Teaching Assistant, University of HullProgramming for Data Science and AI; Fundamentals of Data Science; Understanding Artificial Intelligence; Big Data and Data Mining; Applied Artificial Intelligence.
    2021–2023

Awards

  • Alan Turing Institute Enrichment Scheme — Community AwardNine-month placement within the Turing's cross-disciplinary research community, with development funding.
    2024
  • Office for Students Artificial Intelligence ScholarshipOne of a limited number of £10,000 scholarships for master's study in artificial intelligence.
    2017
  • Departmental Award for Outstanding Academic AchievementHighest overall grade in Arts and Humanities, Manchester Metropolitan University.
    2016
  • Master ScholarAwarded for outstanding undergraduate achievement, Manchester Metropolitan University.
    2016