Professional Context
With 80% of election forecasts relying on data-driven models, hitting a 95% accuracy rate for predictive analytics is crucial for Political Scientists, who must navigate complex datasets and workflow optimization to meet this KPI.
💡 Expert Advice & Considerations
Don't waste time trying to use Gemini for high-level theory crafting; focus on using it to automate data cleaning and visualization, and you'll see a significant reduction in workload.
Advanced Prompt Library
4 Expert PromptsVoter Segmentation Analysis
Using the 2020 US Census data and the Google Cloud ecosystem, design a workflow to segment voters by demographic and create a predictive model for voter turnout based on historical election data, incorporating factors such as age, income, education level, and voting history. Assume a dataset of 100,000 voters and provide a step-by-step guide on how to implement this model using BigQuery and Data Studio. Include a section on data preprocessing, feature engineering, and model evaluation.
Policy Briefing Document Generation
Create a comprehensive policy briefing document on the impact of climate change on global food security, incorporating data from the IPCC, WHO, and FAO. Use Gemini to generate a 5-page document that includes an executive summary, introduction, methodology, results, and conclusion. Ensure the document is formatted according to the APA style guide and includes at least 5 visualizations, such as charts, graphs, and maps, to illustrate key findings.
Social Network Analysis for Protest Movements
Using the Twitter API and Google Cloud's Natural Language Processing tools, analyze the social network dynamics of a protest movement, such as #BlackLivesMatter or #MeToo. Identify key influencers, hashtags, and sentiment trends, and create a network diagram to visualize the relationships between different actors and groups. Provide a step-by-step guide on how to collect and preprocess the data, and include a section on how to interpret the results in the context of social movement theory.
Election Forecasting Model Evaluation
Evaluate the performance of three different election forecasting models (e.g. logistic regression, decision trees, and random forests) using a dataset of historical election results and demographic data. Use Gemini to generate a concise report that includes model metrics such as accuracy, precision, recall, and F1 score, as well as visualizations such as ROC curves and confusion matrices. Compare the performance of the models and provide recommendations for improving the accuracy of election forecasts.