Social Media Data Analytics Course

Lesson 1 • Core Analytics Concepts and Terminology

Defines reach, impressions, engagement, and conversion within a unified vocabulary. Provides the shared language used throughout the entire course.

Lesson 2 • The Social Media Data Landscape

Maps the major platform types, data formats, and volume characteristics unique to social media. Establishes the scope of what analytics can measure and why it matters.

Lesson 3 • The Analytics Workflow

Introduces the end-to-end process from data collection to insight delivery. Students see how each course chapter maps to a stage in this workflow.

Lesson 1 • Authentication and Access Credentials

Covers OAuth flows, API keys, and token management required to access platform data. Students configure secure credential storage to protect access rights.

Lesson 2 • Ethical and Policy Constraints on Collection

Reviews platform terms of service, user consent principles, and data minimisation practices. Ensures students collect data within ethical and policy boundaries from the start.

Lesson 3 • Understanding APIs and Data Endpoints

Explains REST API architecture, endpoints, and request-response cycles in plain terms. Connects API concepts to the specific data types available on social platforms.

Lesson 4 • Collecting Data with Third-Party Tools

Surveys no-code and low-code collection tools for teams without deep programming resources. Compares tool capabilities against direct API access for common use cases.

Lesson 1 • Auditing Raw Social Media Data

Teaches systematic inspection of incoming data for completeness, consistency, and format errors. Students produce a data quality report before any transformation begins.

Lesson 2 • Building a Reproducible Cleaning Pipeline

Packages all cleaning steps into a documented, repeatable workflow using scripts or notebooks. Reproducibility ensures consistent data quality as new data arrives over time.

Lesson 3 • Feature Engineering for Social Data

Creates derived variables such as engagement rate, post age, and content type flags from raw fields. These engineered features directly power the analytical models in later chapters.

Lesson 4 • Handling Timestamps and Time Zones

Resolves inconsistent timestamp formats and time zone offsets common across platforms. Accurate time alignment is essential for trend and engagement analysis.

Lesson 1 • Descriptive Statistics for Engagement Data

Applies mean, median, variance, and distribution analysis to engagement and reach metrics. Reveals skewness and outliers that shape all subsequent analytical decisions.

Lesson 2 • Visualising Social Media Metrics

Selects appropriate chart types for time-series, categorical, and distribution data from social platforms. Effective visualisation accelerates pattern recognition and stakeholder communication.

Lesson 3 • Audience Segmentation Exploration

Uses demographic and behavioural variables to identify distinct audience subgroups within the data. Segmentation findings guide content strategy and targeting decisions.

Lesson 4 • Correlation and Hypothesis Generation

Calculates correlation coefficients between metrics and frames testable hypotheses for deeper analysis. Bridges EDA findings to the modelling techniques introduced in later chapters.

Lesson 1 • Emotion Detection and Aspect Analysis

Extends sentiment to fine-grained emotion categories and aspect-level opinions about specific entities. Enables nuanced brand and product feedback analysis from social conversations.

Lesson 2 • Natural Language Processing Fundamentals

Covers tokenisation, stop-word removal, stemming, and lemmatisation as preprocessing steps for text analysis. These steps form the input layer for all text mining models in this chapter.

Lesson 3 • Machine Learning Sentiment Classification

Trains supervised classifiers using labelled social media text to improve on lexicon baselines. Students compare model performance using precision, recall, and F1 metrics.

Lesson 4 • Lexicon-Based Sentiment Scoring

Applies pre-built sentiment dictionaries to assign polarity scores to posts and comments. Students evaluate lexicon accuracy against manually labelled social media samples.

Lesson 1 • Information Diffusion and Cascade Analysis

Tracks how content spreads through a network over time using cascade and diffusion models. Students identify viral triggers and structural bottlenecks that shape content reach.

Lesson 2 • Centrality Metrics and Influencer Identification

Computes degree, betweenness, closeness, and eigenvector centrality to rank nodes by influence. Results are used to identify key amplifiers and gatekeepers in a network.

Lesson 3 • Community Detection Algorithms

Applies modularity-based and spectral methods to partition networks into meaningful communities. Community structure reveals audience tribes and cross-community information bridges.

Lesson 4 • Graph Theory Basics for Social Networks

Introduces nodes, edges, directed vs. undirected graphs, and weighted relationships in social contexts. Provides the mathematical vocabulary needed for all network analysis techniques.

Lesson 1 • Time-Series Forecasting for Social Metrics

Applies decomposition, ARIMA, and prophet-style models to forecast follower growth and engagement trends. Seasonal and event-driven patterns in social data require specialised forecasting approaches.

Lesson 2 • Audience Behaviour Classification

Trains classifiers to predict user actions such as churn, conversion, or content sharing. Model outputs enable targeted interventions for specific audience segments.

Lesson 3 • Engagement Prediction with Regression Models

Builds linear and gradient-boosted regression models to predict post engagement before publishing. Students interpret coefficients and feature importance to extract actionable content insights.

Lesson 4 • Framing Predictive Problems in Social Analytics

Translates business questions into supervised and unsupervised modelling tasks with clear target variables. Proper problem framing prevents wasted modelling effort and misaligned outputs.

Lesson 1 • Presenting Recommendations to Stakeholders

Converts analytical conclusions into prioritised, actionable recommendations with supporting evidence. Students practise presenting findings and handling data-sceptical stakeholder questions.

Lesson 2 • Storytelling with Social Media Data

Structures analytical narratives using the situation-complication-resolution framework for executive audiences. Data stories that connect metrics to business impact drive faster stakeholder action.

Lesson 3 • Designing a Social Media Measurement Framework

Aligns KPIs to business objectives using a structured goal-metric-target hierarchy. A clear framework ensures every report answers a decision-relevant question.

Lesson 4 • Dashboard Design Principles

Applies data visualisation best practices to layout, colour, and interactivity for analytics dashboards. Students critique and redesign poorly structured dashboards using established principles.