Computational Social Science Intern… at Protagonist · Washington

Summary: Protagonist is a company that combines rigorous analysis with cutting-edge technology to provide strategic recommendations and communication strategies. They are seeking a Computational Social Science Intern who will work on data collection, analysis, and the application of machine learning and natural language processing techniques to derive insights from complex datasets. Responsibilities: - Collect and curate data from a variety of media content aggregators, open-source platforms, and APIs using scripts, scrapers, and automated tools - Build datasets that are relevant to the customer's project scope and need area - Use Python, SQL, or similar languages to clean, structure, and transform datasets for analysis - Apply machine learning and natural language processing techniques to large, unstructured text datasets to uncover meaningful patterns and insights - Implement topic modeling, classification, clustering, and other core NLP/ML workflows aligned with customer analysis needs - Experiment with and evaluate different models and algorithms, including both traditional statistical approaches and modern AI techniques (e.g., transformer-based models, embeddings, stance detection) - Contribute to the design and refinement of analytical frameworks and research methodologies that structure how we assess complex information environments - Help translate social science research questions into computational workflows, bridging theory and applied analysis - Create visualizations and interactive dashboards using tools like Tableau, Superset, Power BI, or similar platforms to communicate analytic findings - Translate complex data outputs into accessible formats that support client understanding and decision-making - Collaborate across teams—including engineering, product, and client delivery—to ensure analytics align with broader project goals - Contribute to client deliverables by packaging and explaining relevant data insights - Participate in the continued development of our Narrative Analytics® platform and workflows, bringing a data-driven mindset to each step of the process - Demonstrate professionalism, ownership, and timely execution across tasks, communication, and deliverables - Adapt to evolving project priorities and fast-paced client timelines, while maintaining quality and clarity - Communicate findings clearly and translate complex technical data science needs into actionable guidance for both external clients and internal team members across technical and cross-functional domains - Collaborate with respect, openness to feedback, and a commitment to continuous learning Required Qualifications: - Authorized to work in the U.S - Must be eligible to work on U.S. Government contracts, which may require U.S. citizenship - Currently pursuing or recently completed a bachelor's or master's degree in data science, Computer Science, Statistics, Mathematics, Political Science, Sociology, Economics, Psychology, International Relations, Communications, or a related field with strong demonstrable computational training - Proficiency in Python and/or R for data analysis, machine learning, and NLP workflows - Strong understanding of SQL and data manipulation techniques - Familiarity with supervised and unsupervised learning methods such as classification, clustering, regression, and topic modeling - Exposure to natural language processing tools and techniques (e.g., tokenization, embeddings, sentiment analysis, transformer models) - Experience building dashboards or data visualizations using Tableau, Superset, Power BI, or similar tools - Intermediate Excel skills, including formulas, pivot tables, and data cleaning functions Preferred Qualifications: - Familiarity with Git, Jupyter, or collaborative development tools - Understanding of cloud platforms (e.g., GCP, AWS) or large-scale computing workflows (e.g., distributed processing, data pipelines) - Experience working with social media, news, or open-source text datasets - Exposure to computational text analysis beyond keyword search (e.g., word embeddings, document similarity, stance detection, narrative framing) - Interest in or familiarity with political communication, media analysis, international security, or public policy environments - Ability to explain technical concepts clearly and translate data into insights for both technical and non-technical stakeholders - Strong organizational and time management skills with attention to detail - Comfortable working independently and collaboratively in a fast-paced, evolving environment Required Skills: Python, R, SQL, Data manipulation, Supervised learning, Unsupervised learning, Classification, Clustering, Regression, Topic modeling, Natural language processing, Tokenization, Embeddings, Sentiment analysis, Transformer models, Data visualization, Tableau, Superset, Power BI, Excel, Formulas, Pivot tables, Data cleaning, Git, Jupyter, Cloud platforms, GCP, AWS, Distributed processing, Data pipelines, Computational text analysis, Word embeddings, Document similarity, Stance detection, Narrative framing, explain technical concepts Internship Start Date: Start in 2026 Summer