DiscoverText

Overview

DiscoverText is a cloud service for multilingual text analysis, annotation, and document review. It best suits research and eDiscovery teams that need human coding alongside machine classification. Its breadth is compelling, but social-data collection limits and costly enterprise access narrow its fit.

Key features

Machine classification and human coding

Users can build reusable classifiers, called sifters, to find relevant items and sort text into topics, sentiment, or other categories. Combining these with human annotation, crowdsourcing, adjudication, measurement, iteration, replication, and annotator ranking supports workflows where automated coding needs human oversight. That combination is useful for substantial research projects, but may be more machinery than a team seeking only basic text analysis needs.

The service is intended for free text and metadata from sources such as surveys, customer feedback, CRM, chats, email, public comments, and RSS feeds. Its social-data limits matter: DiscoverText can no longer collect Twitter data in real time and has not been connected to Facebook’s open API since 2014. Researchers can upload non-Twitter social data they already have in spreadsheets, but should not choose it to gather fresh data from those platforms.

eDiscovery and API

Deduplication and automated clustering can organize near-duplicate documents; redaction can produce PDF collections with Bates stamps and spreadsheet indexes. This makes DiscoverText relevant to teams handling document review as well as text analysis. API access is restricted to licensed Enterprise users granted an API key. Its documented operations cover projects, archives, buckets, datasets, deduplication, clustering, and tag clouds; search, word-cloud creation, and some reporting are forthcoming, so API buyers should account for those gaps.

Pricing

The free plan and trial make it possible to assess the service before paying, though the trial terms are inconsistent: the pricing page describes up to 30 days with enterprise-level features, while the signup page calls it a 7-day free trial.

• Professional: 99.00 USD per month, billed $99 / month. It includes 100,000 Units, 25 Live Data Feeds, 1 Professional Seat, 0 Enterprise Seats, unlimited projects, analytic and reporting tools, adjudication tools, Cloud Explorer, standard support, and Gnip availability. This is the practical paid starting point for an individual professional needing core analysis and adjudication; the single seat and absence of Enterprise Seats constrain team use.
• Enterprise: 3000.00 USD per month, billed $3,000 / month. It includes 1,000,000 Units, 100 Live Data Feeds, 1 Enterprise Seat, 2 Professional Seats, unlimited projects, Top Meta, Active Learning, interactive histograms, the FOIA Toolkit, priority support, and Gnip availability. The added seats, quotas, and tools suit larger or more demanding workflows, but the price is a substantial step up from Professional.
• Custom Enterprise: custom pricing for a custom account package. It is the option for buyers whose requirements do not fit the two fixed plans.

Academic users have a distinct route: students and professors can receive free access, training, and project support directly from the founder, and academic group licenses are 100% free. The API is not a general-purpose add-on; it requires a licensed Enterprise account and an API key.

Platforms

DiscoverText is cloud-deployed and available on the web, with API access for eligible Enterprise license holders. The API requirement makes the higher-priced tier especially relevant to teams planning a programmatic workflow.

Who it's for

Research teams working with large multilingual text collections can benefit from the mix of reusable classification, human review, and academic access. Document-review teams may also value deduplication, near-duplicate clustering, and redaction outputs. It is a weaker fit for buyers whose priority is collecting current Twitter or Facebook data, or who need API access without an Enterprise license.

Pros and cons

• Pro: Reusable sifters pair with human annotation and adjudication, supporting projects that need both automated classification and review.
• Pro: Deduplication, clustering, and Bates-stamped redaction outputs extend the product beyond text analysis into eDiscovery workflows.
• Pro: Free academic access, training, project support, and group licenses make it unusually accessible to academic users.
• Con: Real-time Twitter collection is no longer supported, and Facebook’s open API connection ended in 2014, limiting social-data gathering.
• Con: API access requires an Enterprise license and granted key, while the documented API still lacks search, word-cloud building, and some reporting operations.
• Con: Enterprise costs 3000.00 USD per month, far above Professional, and Professional has only one seat and 100,000 Units.
• Con: Trial duration is presented as both up to 30 days and 7 days, so prospective users should confirm the applicable term.

Alternatives

Choose Dovetail if its free plan’s one channel, one project, basic chat, and AI summaries cover the need; Enterprise pricing is custom. For a free option on web, Windows, macOS, and Linux, consider CATMA. spaCy is a free alternative for Windows, macOS, and Linux. Speakerbox is free on Linux, macOS, and Windows. Taguette is free on web, Windows, macOS, and Linux. KH Coder offers a freemium option for Windows and macOS. QualCoder is free on Windows, macOS, and Linux. T-LAB is free on Windows. Browse Text Analytics Software or Social Media Analytics Software for more options.

Verdict

Choose DiscoverText if your research or document-review work benefits from human-reviewed machine classification, eDiscovery tools, and, for academic users, free access and support. Look elsewhere if fresh Twitter or Facebook collection is central, or if you need API access without Enterprise pricing.