About Our Text Analysis
& Data Science Software

Collaborative text analytics

With dozens of powerful, multilingual, text mining, data science, human coding, and machine-learning features, DiscoverText provides cloud-based software tools to quickly evaluate large amounts of unstructured free text, survey responses, public comment to government agencies, and other text data. Find out why we are ranked #1 for text analysis and trusted by hundreds of academic research groups.

Start a Free Trial

“Born on the Internet &
Designed with Network Properties.”

Collect, clean, and analyze text data

Unstructured text data is messy

Data scientists working in text analytics 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 topic, sentiment, and other categories. DiscoverText combines data science methods with e-discovery text analytics tools to shorten a process that used to last weeks or months; our machine-learning sifters are created in hours or just a few minutes using crowdsourcing. We support technical integrations with Twitter and SurveyMonkey. Academics trust DiscoverText to help them do better, more transparent research, resulting in more scholarly publications.

Subscribe Today

Humans and machines learn to classify text

Point and click technology that anyone can master

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 text analytics software and data science methods originate in a decade of NSF-funded research into the measurements that accelerate machine-learning. Text classification is an old, hard problem. Our method of adjudication creates gold standard training sets to improve machine-learning by ranking human annotators over time. Our patented CoderRank approach is critical for accurate, reliable results.

eDiscovery tools that work

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 the digital footprint of viral Tweets. With public comment data, these groupings are form letters and modified forms. In large-scale surveys, duplicates and near duplicates are frequently held but independently expressed opinions among customers or employees. Our interactive machine classifier histograms allow data science teams to identify the items in a collection that add the most value when coded by humans. These text analytics tools enable purposive sampling that further accelerates the process of training machine classifiers.

Start a Free Trial

All Text Analytics are Filters

Filter by date, geo, place name, influence, networks, or numerous other metadata values. Use unigrams, bigrams, and trigrams via our CloudExplorer to probe raw data. Create and save complex search queries, human coding schemes, or just filter on active-learning machine classification scores. Stack multiple filters for highly refined yet easily accessible custom text analytics results. Our favorite filter is “items not coded” but there are many others that underscore why “all text analytics ultimately can be seen as filtering.” – Stu Shulman, Founder & CEO

Subscribe Today

DiscoverText: “One of the 5 Best Integrations to
Help Analyze Your SurveyMonkey Data”

Boolean defined search, n-grams, word clouds, and custom topic dictionaries are power tools for text analysis and machine-learning

Discover central topics and also elusive but valuable unexpected or rare concepts. Use this information to train machine-learning classifiers to recognize relevant text and social media data. Jump into data using an interactive word CloudExplorer or build a mini topic dictionary using “defined” search. Try our new listview for seeing the top 300 bigrams and trigrams in your data

Start a Free Trial