Collaborative text, survey, and twitter data analytics
With dozens of powerful text mining, human coding, and machine-learning features, including access to free Twitter Search API as well as premium Gnip PowerTrack 2.0 Twitter data, DiscoverText provides cloud-based software tools to quickly evaluate large amounts of text, survey, and Twitter data.
Collect, clean, and analyze text data
Unstructured text data is messy. Data scientists know cleaning data is time consuming. Users of DiscoverText build reusable custom machine classifiers or “sifters” to find the most relevant items before sorting them into topics and sentiment categories. DiscoverText shortens a process that used to last weeks or months; our machine-learning sifters are created in hours or when using crowd sourcing, even in just a few minutes. We support technical integrations with Twitter and SurveyMonkey. Academics trust DiscoverText to help them do better, more transparent research, resulting in publications.
Humans and machines must learn together how best to classify text
Humans are good at some things and computers are good at others. A consistent back and forth between humans and machines increases the ability of both to learn. Our software originates in a decade of NSF-funded research into the measurements that accelerate machine-learning. Text classification is an old, hard problem. DiscoverText keep human in-the-loop during an ActiveLearning process. Our method of adjudication creates gold standard training sets to improve machine-learning and helps to rank human annotators over time.
Cluster unstructured information automatically
Deduplication and automated clustering of near-duplicates gives users a high level sense of the data landscape. With Twitter data, these groupings are a roadmap to digital footprint of viral Tweets. Interactive classifier histograms identify the items in a collection that add the most value when coded by humans. These tools enable purposive sampling that further accelerates the ActiveLearning process of training classifiers.