Top companies trust Datastreamer to integrate, enrich, join, and apply their web data needs.
Find out the subjects the users are talking about. Classify content by topic. Intelligently deduce geographic region.
Super granular. Supports IPTC, IAB, and Wikidata IDs.
Also known as: theme identification, subject detection, or key topic recognition. Topic extraction determines the dominant topics in the text.
Tisane provides the topics at a document level.
When a particular word has multiple interpretations, the sense of the word must be determined in the current context. For example, Jupiter is a planet and a Roman deity. Whether it's the planet or the deity, depends on the text.
For example, the sentence Juno is the wife of Jupiter refers to the deity. Tisane determines the relevant topics as Roman mythology, supernatural (gods), relationship, and family (since the spousal connection is mentioned).
There are common taxonomy standards that Tisane can provide::
native - native Tisane topic names; based on standard English terms for the topic. The default standard.iptc_code - codes of the IPTC (International Press Telecommunications Council) Media Topics classification - a standard used in the media.iptc_description - English descriptions of the IPTC codes.iab_code - codes of the IAB (Interactive Advertising Bureau) content taxonomy.iab_description - English descriptions of the IAB codes.wikidata - Wikidata codes (usually of the form Qnnnnn, e.g. Q123).Aggregated content from over 2,000 Chinese blogs and over 200,000 diverse English blogs, capturing the pulse of conversations. From niche interest to mainstream topics, Socialgist dataset provides a window into the vast array of perspectives, trend and insights that blog uniquely offer. Harness this rich resource for nuanced understanding of public sentiment, emerging trends, and influential bloggers in various domains.
How Datastreamer works
Quickly apply Tisane Topic Extraction to Socialgist Blogs with a Datstreamer Pipeline.
Web data is an essential component of enterprise data pipelines, enabling organizations to integrate structured and unstructured data from partner APIs, legacy systems, and public web sources.
Make your web data work harder. With Datastreamer, you can enrich, filter, join, structure, store, or search data effortlessly using hundreds of out-of-the-box operations.
Web data, unlocked. Datastreamer empowers you to expand your Pipelines as needed while removing friction from your operations.
Add Datastreamer components to your data stack and explore its full capabilities
