Uside: Analyzing employee surveys to monitor conduct of change

Analyze employee surveys to support change

Uside is the first consulting firm specialized in cultural and behavioral changes.

With its unique expertise in studying behavior based on a scientific methodology, Uside's team of 70+ experienced senior consultants works with over half of France's CAC 40 companies. In doing so, Uside creates and develops the conditions for a positive dynamic of adaptability by making people the driving force behind sustainable performance.

In partnership with Uside, Lettria worked on a solution to automate employee survey analysis for a company in the energy sector.

Analyze emotions and identify solutions from a large panel of responses

Faced with a massive reorganization of its teams, the client wanted to interview its managers in order to collect their feelings and consider solutions to improve internal change management.

More than 200 workshops were organized during which 1,800 participants shared their opinions on "good practices" to be implemented. These workshops were divided into three parts: first, three good practices were submitted, then there was a collective brainstorming session, and finally more free suggestions.

The workshops were a great success, yielding over 1,300 results. But with success came a challenge, as manually processing that many texts is not tenable due to the processing costs and risk of human error.

Lettria and Uside therefore proposed a solution to automate the analysis and synthesis of the texts.

Automating the analysis and summarization of transcripts using NLP

To guarantee accurate data processing, Lettria proposed an analysis using a sequence of technical approaches to determine the main axes, or trends, that could emerge from these workshop feedback sessions.

• Facilitate reading thanks to lemmatization

Thanks to lemmatization, i.e. the morphological analysis of a text by simplifying words, we were able to standardize the texts. The objective was to gather synonyms and close formulas to build a more harmonized word cloud. With this perspective, it is possible to identify the key elements of the transcripts and to save time without getting lost in the text.

• Isolate key words using Pos-Tagging

To refine this process, Lettria uses Pos-Tagging to retain only verbs and common nouns. Conjunctions, determiners and other minor tags are not processed. Only meaningful words are kept and analyzed.

• Contextualize using the dependency links between words (Dependency Matcher)

Once the text is segmented and the main words are isolated, we use the Dependency Matcher to give meaning to the different components of the text. Adjectives are linked to the corresponding nouns, object complements to verbs, etc., in order to contextualize the main ideas. Without Lettria's solution, it is impossible to combine these words and accelerate data processing, which in turn would prevent the client from (quickly) identifying the essential axes.

• Analyze emotions

The objective is to understand, through sentence constructions, adjectives, and more what feelings are associated with each issue evoked in the surveys. In this way, it is possible to determine the positive or negative opinions of employees based on the topics and comments.

In practice, the most present and important words stand out and are associated with a color that represents a feeling. Taken all together, we were able to present the main analytical axes.

Best practices white paper

Between development and execution, the project took place over roughly 2 months. The processing of the results allowed the company to produce a white paper of "best practices" to facilitate its reorganization and the acceptance of those changes by its employees.

The tool, developed in part using Lettria technology, now exists as a turnkey solution making it possible to update, refine, modify or add new survey results to perfect the analysis. New transcripts can be added directly to the interface. The conclusions can thus continue to be enriched and adjusted according to management feedback as the project progresses.