Master's Thesis - LLM-Based Narrative Virality Analysis and Signal Design in Economic and Market Text

Siemens Energy
Erlangen, Germany
2 months ago

Role details

Contract type
Temporary contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Job source

Tech stack

Artificial Intelligence Text Mining Data Processing Large Language Models Information Technology Data Analytics Text Analysis

Job description

You work with public economic and market-related text and investigate how narratives spread across sources and time. Your focus is on exploring LLM-based methods for measuring narrative spread, salience, and persistence, and on transforming these dynamics into structured and interpretable signals. How You’ll Make an Impact

  • Development of a research framework for measuring narrative spread and salience in public economic and market-related text
  • Exploration of LLM-based and clustering-based methods for identifying coherent narrative themes across sources and time
  • Implementation of a prototype for virality-oriented or spread-based signal generation from textual data
  • Evaluation of different dimensions of narrative spread, such as speed, source diversity, persistence, and cross-source propagation
  • Documentation of methodology, findings, and limitations for future reuse in applied text and data analytics
  • Support with the translation of research outcomes into interpretable signal concepts for forecasting-related use cases

Requirements

Do you have experience in Research?, Do you have a Master’s degree?, * Studies in Data Science, Computer Science, Artificial Intelligence, or a related field at Master’s level

  • Knowledge of Python-based data processing , NLP, or text-mining workflows for text analysis and prototyping
  • Interest in large language models, prompt-based methods, narrative analysis, and information diffusion in economic, business, or market-related settings
  • Understanding of clustering, similarity analysis, or time-based signal construction for text-driven indicators
  • Ability to work independently on implementation, analysis, and technical documentation in an applied research environment
  • Experience with embeddings, public text datasets, event analysis, or experimental evaluation as an advantage

About the company

At Siemens Energy, we are more than just an energy technology company. With ~100.000 dedicated employees in more than 90 countries, we develop the energy systems of the future, ensuring that the growing energy demand of the global community is met reliably and sustainably. The technologies created in our research departments and factories drive the energy transition and provide the base for one sixth of the world’s electricity generation.

Our global team is committed to making sustainable, reliable, and affordable energy a reality by pushing the boundaries of what is possible. We uphold a 150-year legacy of innovation that encourages our search for people who will support our focus on decarbonization, new technologies, and energy transformation. Find out how you can make a difference at Siemens Energy: https://www.siemens-energy.com/employeevideo Our Commitment to Diversity Lucky for us, we are not all the same. Through diversity we generate power. We run on inclusion and our combined creative energy is fueled by over 130 nationalities. Siemens Energy celebrates character - no matter what ethnic background, gender, age, religion, identity, or disability. We energize society, all of society, and we do not discriminate based on our differences. Rewards/Benefits

  • Exciting insights into an international company
  • Lay the foundation for your career with us

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:04 min

Extracting unique term frequencies efficiently for text analysis

Mihailo Joksimovic · World Congress 2022

2:35 min

Machine learning opportunities within audience interaction platforms

Marek Suppa · LIVE

1:32 min

Structuring platforms for new services and data analytics

Nevelina Aleksandrova · LIVE

3:55 min

Implementing sentiment analysis pipelines on ingested text

Iulia Feroli Iulia Feroli · LIVE

1:10 min

Introduction to Microsoft Fabric and data agents

Dr. Alexander Wachtel Dr. Alexander Wachtel +1 · World Congress 2025

50 sec

Identifying real-world applications for stream processing technology usage

Soroosh Khodami Soroosh Khodami · World Congress 2024

Videos

See all

Related articles

See all