The largest social media taxonomy for healthcare

Classification of Healthcare Social Media Data

Symplur Signals uses a combination of human curation and automated processes such as Natural Language Processing (NLP) and our proprietary algorithms to organize, structure, and appropriately categorize raw social media data, creating order out of chaos. We classify the data by type and by subject matter:

Datasets by type: Our data classification process has aggregated and organized an expanding catalog of over 35,000 curated and searchable terms, or datasets, that include hashtags, Twitter usernames and keywords, allowing you to identify and locate healthcare tweetchats, conferences, influencers, and more. Each one of these datasets contains conversations, individuals, and entire communities that share something in common.

Datasets by subject matter: Classifying and indexing conversations into collections that fall under one overarching topic enhances the probability of discovering previously unknown similar or related topics and hashtags that reveal more pertinent data, specialized online communities, and valuable influencers. For instance, when searching our datasets for lung cancer you will discover other related or similar datasets such as “lung cancer social media,” “lung cancer treatment,” “lung cancer caregiving,” “lung cancer screening.” Each dataset encapsulates relevant conversations and distinct online communities that may not have overlapped with your original search term.