The Text analysis module facilitates qualitative analysis using artificial intelligence. It includes a keyword search, sentiment analysis, and theme analysis. Text answers include text answer questions (open-ended questions) and comments.
A Large Language Model (LLM) is used to extract sentiment from text by analyzing the tone, language and context of the words used. The model looks for specific indicators of emotion, such as positive or negative words, expressions of satisfaction or dissatisfaction, and the general feeling conveyed by the text. By analyzing the content of the text and comparing it with a list of themes provided, the model can also associate themes with the text.
Since a message may contain several distinct and relevant pieces of information, replies and comments are broken down into quotes. For more context, the full commentary is available by clicking on the extract.
Although our goal is to provide you with relevant results, errors or omissions might happen in some cases:
- The context in which the comment was made is ambiguous
- Information is vague or inconsistent
- Subtle nuances haven’t been taken into account
In such cases, IA results might be inaccurate.
Text analysis attributes
Sentiments
Extracts from comments and open-ended responses are classified into 6 sentiment levels:
- Very positive
- Positive
- Neutral
- Negative
- Very negative
- Mixed
Themes
Some quotes will also be automatically linked to one of the predefined themes listed below. If we cannot match a quote to a theme, it will be classified as “No theme”.
| Theme | Definition |
|---|---|
| Care and interventions | Focuses on the patient's experience following his admission, during medical care and procedures, ensuring the quality and effectiveness of interventions, as well as the responsiveness and expertise of the staff. |
| Interpersonal skills | Interpersonal skills of healthcare staff, including their ability to demonstrate understanding and sensitivity to patients' feelings and experiences as well as the importance of paying special attention to patients' needs and concerns. |
| Waiting | Waiting times for appointments, emergencies, and surgical interventions. |
| Information | Availability and quality of educational information provided to patients about their health condition, preparation for treatments, and details of medical procedures, as well as the clarity and effectiveness of communication between patients and various medical and administrative staff members. |
| Support | The reassuring presence and emotional support provided to patients, as well as the referral to additional support resources. |
| Access | Ease of access to care, specialists, preventive services, and medications, ensuring equal access for all patients. |
| Comfort of the care environment | The pleasantness and comfort of the environment across all care spaces, including the patient room, the operating room, and shared areas. |
| Preferences | Individual choices regarding treatment and care processes, adapting health services to the patient's personal, cultural, and religious preferences. |
| Pain management | Proper and effective pain management for patients to improve their comfort and recovery. |
| Coordination | Organization and collaboration among different healthcare professionals to effectively meet patients' needs. |
| Continuity and transition | Careful coordination between different phases of care and transitions between healthcare facilities, providing a safe and seamless patient experience. |
| Family and close ones | The involvement of the patient's family and friends in the care process, recognizing their important role in support and decision-making. |
| Quality of meals | The nutritional input and taste quality of meals served to patients, recognizing the importance of nutrition in the healing process. |
| Reception/admission | The quality and smoothness of the patient's reception and admission processes. |
| Cleanliness | The level of cleanliness and hygiene of the healthcare facility, with an emphasis on infection prevention. |
| Autonomy | Patients’ involvement regarding the choice of their treatment, enhancing their ability to manage their health independently. |
| Privacy | Patients’ privacy during care, ensuring that interactions and treatments respect their personal dignity. |
| Language | Whether the information and communications are provided in the patient's preferred language for optimal understanding. |
| Rights | Patients' rights are respected, including the right to information, informed consent, and the protection of their integrity. |
| Confidentiality | The security of patients' personal and medical information, ensuring that their confidentiality is maintained at all times. |
Quote Type
In addition to themes and sentiments, analyzed quotes are matched to a type that allows you to easily identify the nature of the comment.
| Type | Definition | Examples |
|---|---|---|
| Potential issue | The quote seems to indicate that the patient’s health and/or safety were endangered. | • Mentions of medical or procedural mistakes • Perceived negligence that may cause harm • Mentions of acts of violence (physical, psychological or sexual) • Severe symptoms, significant emotional distress, suicidal thoughts or self-mutilation |
| Praise | The quote seems to express gratitude for an individual, a team or a service. | • A quote describing a positive interaction with a nurse or a doctor • Highlighting the quality of a specific service |
| Suggestion | The quote includes specific and achievable recommendations to improve patients’ experience. | • Ideas for new policies or services • Suggestions for adjusting existing infrastructures or procedures • Suggestions for improving existing tools or technologies |
Enable or disable text analysis on a question
The text analysis feature is enabled by default when creating a question. You can enable or disable it individually for text answer questions, comments and/or other choices.
- Access the Surveys list via the main navigation.
- Click on the survey you want to edit.
- Click on the Edit button.
- Click on the question you want to edit.
- Enable/disable the “Analyze sentiments found in the answers“ option using the switch (text answer questions and/or comments).
- Save the question.
Analyze text responses from a questionnaire
- Access the list of Surveys via the main navigation.
- Click on the survey.
- Click on the Text analysis tab.
- Click on a quote to see the complete comment.
Filter quotes
- Access the list of Surveys via the main navigation.
- Click on the survey.
- Click on the Text analysis tab.
- Filter your quotes by a specific date or period of time.
- Click on Filters to see the answers to one or several specific questions, to exclude dropouts or to target a specific group of respondants.
Export quotes
- Access the list of Surveys via the main navigation.
- Click on the survey.
- Click on the Text analysis tab.
- Click on Export.
- Choose your export parameters and click on Download.
Generate a summary by theme (bêta)
Save a lot of time and simplify your analysis by using our AI-powered Summary feature. In just a few clicks, get a summary of the last 500 quotes attached to a theme.
- Access the list of Surveys via the main navigation.
- Click on the survey.
- Click on the Text analysis tab.
- Click on a theme.
- Click on Summarize.
- If you wish, use the Copy-paste icon.
- If you wish, click on Regenerate to get a different summary.