# Discussion Share Graph ### **Overview** The Discussion Share Graph measures how the share of conversation around specific topics, brands, or products evolves over time across social platforms such as TikTok. TickerTrends analyzes large volumes of social posts, categorizes them by topic or entity, and calculates each one’s **share of total discussion** within a defined dataset. This approach captures how attention is distributed across competing narratives in real time. Rather than tracking engagement or sentiment alone, the graph focuses on **relative attention**, showing what proportion of the overall conversation each topic occupies. Increases in discussion share often reflect rising awareness, stronger narrative momentum, or increased creator-driven amplification **Customization**\ Discussion Share graphs can be customized to focus on specific entities and segments within the dataset. Users can: * Add or remove entities to define a custom comparison group * Toggle individual segments on or off directly in the graph * Refine the view to isolate specific narratives or product categories These controls allow for more targeted analysis by reducing noise and focusing only on the most relevant portions of the discussion. ### **Historical Length** Coverage typically extends multiple years back depending on platform data availability, allowing users to analyze how narratives evolve across different market cycles and product lifecycles. ### **Granularity** Data is processed at daily granularity, enabling users to observe rapid shifts in attention driven by viral content, news events, or product releases. ### **Update Frequency** Updated daily with a short delay, ensuring near real-time visibility into changing social dynamics. ### **Methodology** TickerTrends processes large-scale social data and applies classification models to group posts by topic, brand, or product. Each post contributes to a broader dataset of total discussion volume. The model then calculates the proportion of total discussion attributed to each entity over time. The output reflects **relative share of conversation**, allowing users to track how attention shifts across competing topics. This is designed to capture **directional changes in narrative and attention**, not absolute mention counts. ### **Example Visualization**

#### **Use Cases** Identify emerging trends and topics gaining social traction.\ Track shifts in narrative momentum across competing products or brands.\ Detect early attention signals before they translate into measurable demand.\ Combine with Market Share and Search data to understand how attention converts into behavior. **Discussion Share Graph Controls:** Enables users to select or remove sections within the graph to focus on specific segments of discussion data. **Discussion Share Decomposition:** Discussion Share Decomposition allows users to break down any topic into its core drivers on social media/google search trend and see what’s driving conversation in real time - including emerging trends.