The new version focuses on text mining in the post-pandemic era, gaining crucial insights using sophisticated text analysis capabilities designed for both novice data analysts and skilled data scientists and in all languages.

Provalis Research announces the availability of a new version of WordStat text analysis software version 9. This new version is designed to allow easier market adoption of text analysis across organizations, large and small, while contributing to their ability to make decisions with higher levels of agility.

Marketing Technology News: Strata Introduces Identity Orchestration Platform for Multi-Clouds

The COVID-19 pandemic caused historical data to become obsolete, while requiring rapid change acceleration, which is now crucial for the survival and the resilience of organizations. This led Gartner to predict that 70% of organizations will shift their focus from big data towards small and wide data by 2025. Given that 80% of available business information is mostly unstructured text data, this shift will require important adjustments for organizations of all scales. Businesses will require addressing data from shorter time periods, while mobilizing a large number of data sources from the same period, thus relying on wide and small data. This new approach empowers both novice analysts and proficient data scientists to conduct text analysis per division or even department on an organizational level.

“Wordstat 9 turns the organization’s challenges into practical and effective text analysis actions distributed across the organization, no matter what the level of expertise of the employee,” says Normand Péladeau, CEO of Provalis Research. “We focused on building a user interface that can be used by non-programmers and programmers alike to expedite data mining within the organization,” adds Péladeau.

Organizations with limited programming resources can reduce the volume of programming requests by incorporating Python and R routine scripts with general purpose user interfaces to benefit from text transformations, powerful spelling corrections, unique text analysis routines, data visualization, and an unsurpassed categorization system. Wordstat 9 also increases interactivity levels through new features to analyze co-occurrence as well as the relationship between unstructured text and structured data, allowing for deeper text analysis insights.

Marketing Technology News: MarTech Interview with Navdeep Saini, Co-founder and CEO at DistroScale

WordStat imports information from diverse data sources with automatic data cleaning features that ensure focus on meaningful information. Apart from directly importing from MS Excel, MS Word, PDF, SPSS, Stata, social media, e-mail, and web survey platforms, version 9 also allows importation of news transcripts from the LexisNexis and Dow Jones’s Factiva output files.

WordStat is a language-independent text mining software ideal for sorting through diverse data sources. This means that the software requires no further translation of data and is now available to a greater number of researchers, particularly with the inclusion of languages such as Chinese, Japanese, Thai, Korean, etc. In order to treat text more accurately, Wordstat 9 also features a much faster and more accurate spelling correction engine. This feature allows for on-the-fly automatic spelling correction, particularly useful for analyzing social media and web survey data.

Importantly, it is now also possible to create pre- and post-processing scripts, performing custom analysis on the original or transformed text data or on quantified results obtained through content analysis of these documents. This feature offers endless possibilities to extend the capabilities of WordStat, such as implementing new machine learning algorithms, advanced statistical modeling techniques, or custom data transformation. Sample scripts have been included to compute text readability metrics, detect languages, apply other topic modeling techniques (LDA or STM), or to create predictive models using machine learning (SVM, Neural Network, Decision Tree, etc.).