Healthcare Chatbot Interaction Logs

This dataset provides detailed, structured logs of healthcare chatbot interactions, capturing every message exchanged, detected intents, response times, and user feedback. It enables comprehensive analysis of patient engagement, chatbot performance, and conversational trends, supporting improvements in digital healthcare delivery and patient satisfaction.

  • last updated 21 Jul 2025
  • by GoMask
The brief that made it

Analyzing patient engagement and satisfaction with digital health chatbots

Sample rows

preview · 8 of 200 rows · all 16 columns
interaction_idstringlanguagestringresponse_time_msintegerresolvedbooleanchatbot_idstringuser_idstringmessage_idstringmessage_timestampdatetimesender_typestringintentstringentitiesstringsession_start_timedatetimesession_end_timedatetimeuser_feedback_ratingintegeruser_feedback_textstringmessage_textstring
sess_1001enblankblankcb_alphapat_01msg_000012023-04-25T09:01:05Zusersymptom_reportheadache,fever2023-04-25T09:01:05Z2023-04-25T09:05:31ZblankblankHi, I'm feeling a headache and slight fever.
sess_1001en2200blankcb_alphapat_01msg_000022023-04-25T09:01:07Zchatbotask_durationblank2023-04-25T09:01:05Z2023-04-25T09:05:31ZblankblankI'm sorry to hear that. How long have you had these symptoms?
sess_1001enblankblankcb_alphapat_01msg_000032023-04-25T09:03:54Zuserprovide_duration2 days2023-04-25T09:01:05Z2023-04-25T09:05:31ZblankblankIt's been about two days now.
sess_1001en1800blankcb_alphapat_01msg_000042023-04-25T09:05:29Zchatbotoffer_optionsblank2023-04-25T09:01:05Z2023-04-25T09:05:31ZblankblankThank you for sharing. Would you like advice or to book an appointment?
sess_1001enblanktruecb_alphapat_01msg_000052023-04-25T09:05:31Zuserblankblank2023-04-25T09:01:05Z2023-04-25T09:05:31Z5The chatbot was very helpful. Booking was easy.Book an appointment, please. The chatbot was very helpful.
sess_1002esblankblankcb_betapat_13msg_000062023-06-03T16:52:11Zuserappointment_requestcita,hijo2023-06-03T16:52:11Z2023-06-03T16:56:22ZblankblankNecesito pedir una cita para mi hijo.
sess_1002es2500blankcb_betapat_13msg_000072023-06-03T16:53:44Zchatbotask_datetimeblank2023-06-03T16:52:11Z2023-06-03T16:56:22Zblankblank¿Para qué fecha y hora desea la cita?
sess_1002esblankblankcb_betapat_13msg_000082023-06-03T16:54:08Zuserprovide_datetimeviernes,10:002023-06-03T16:52:11Z2023-06-03T16:56:22ZblankblankEl viernes a las 10 de la mañana.

What the 200 rows show

from the 200-row sample

En language stands out: mean response_time_ms is 1,698, against 2,469 for the rest.

  • 70%resolved = true
  • 2,000median response_time_ms
  • 2sender types
  • 43users
  • 43intents
  • 4median user_feedback_rating
Mean response_time_ms by language82 rows
02,0004,0001,698en62 rows2,298es12 rows2,725fr8 rows
response_time_ms82 rows, in bands of 500
01530401521271501,5003,000response_time_ms →

Median 2,000, from 0 to 3,000.

chatbot_id200 rows · 6 values
  1. cb_beta50
  2. cb_alpha49
  3. cb_gamma40
  4. cb_delta24
  5. cb_epsilon23
  6. cb_extreme14
16 columns by typefrom the column list below
  • string 10
  • integer 2
  • datetime 3
  • boolean 1

Columns

16 columns in four groups
blueprint · 16 columns
columntypedescriptionexample
Text 10 columns
interaction_idstringUnique identifier for each chatbot interaction session.uniquesess_1001
user_idstringUnique identifier for the patient or user interacting with the chatbot.pat_01
chatbot_idstringIdentifier for the specific chatbot instance handling the interaction.6 chatbotscb_alpha
message_idstringUnique identifier for each message exchanged during the interaction.uniquemsg_00001
sender_typestringIndicates whether the message was sent by the user or the chatbot.user · chatbotuser
message_textstringThe actual text content of the message exchanged.N/A
intentstringThe detected intent or purpose of the message (e.g., symptom_report, appointment_request, medication_query).optionalsymptom_report
entitiesstringComma-separated list of key medical entities or keywords extracted from the message (e.g., symptoms, medications, dates).optionalheadache,fever
languagestringLanguage code of the message content (e.g., en, es, fr).4 languages · optionalen
user_feedback_textstringOptional free-text feedback provided by the user at the end of the session.optionalVery poor experience.
Numbers 2 columns
response_time_msintegerTime in milliseconds taken by the chatbot to respond to the user's message. Null if sender_type is 'user'.0 or more · optional2200
user_feedback_ratingintegerUser's feedback rating for the chatbot session (1-5 scale).1 to 5 · optional5
Dates and times 3 columns
message_timestampdatetimeTimestamp indicating when the message was sent or received.2023-04-25T09:01:05Z
session_start_timedatetimeTimestamp when the interaction session started. Same for all messages in the session.2023-04-25T09:01:05Z
session_end_timedatetimeTimestamp when the interaction session ended. Same for all messages in the session.2023-04-25T09:05:31Z
True or false 1 column
resolvedbooleanIndicates whether the user's issue was resolved during the session.optionaltrue

Use it for

  • resolved70%38 of 54 rowsmean response time ms…1,698en2,298es2,725fr

    A healthcare dashboard

    The resolved rate, response_time_ms by language and a breakdown of chatbot_id. Excel, Power BI or Tableau.

  • Why do the 62 en rows have a mean response_time_ms of 1,698?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable interactions with user_id, chatbot_id and message_id to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 16 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows16 columns
Yours1,000 rows16 columns

blueprint · healthcare-chatbot-interaction-logs

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 16 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • JSON logs for each session.
  • Intent recognition and response outcomes tagged.
  • Session duration and escalation status included.
  • User sentiment detected from message content.
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
healthcare-chatbot-interaction-logs

More in Healthcare

Browse all
Also in HealthcareHealthcare Symptom Progression DiaryClaims Denials and Rejection ManagementPatient Medication Adherence LogsAll 1,967 datasets

What should your data show?

Preview 20 rows free
No signup. No card.