Home / DialogFlow ES / How do you measure your Dialogflow bot’s accuracy
Analytics | DialogFlow ES

How do you measure your Dialogflow bot’s accuracy

Website Name Change

I have changed the name of this website from Mining Business Data to BotFlo. I am offering a 60% off discount on both my Dialogflow ES and Dialogflow CX courses till April 20th 2021 for people who can help me spread the word about my new website.

In 2021, you should consider using a tool like Airtable (rather than Chatbase) to measure your Dialogflow bot’s accuracy, especially when your bot is at low volume. I explain why in the video below.

Chatbase vs Airtable for measuring Dialogflow accuracy

The U-M-M method

A while back, I wrote a post which linked to Chatbase’s UMM method which provides a way to reason about your chatbot’s accuracy. While it is a good idea and I do derive some ideas from it, it is not particularly useful because there isn’t any way to measure the accuracy using the UMM method.

What I am proposing here is much simpler[1].

The confusion matrix

You may be familiar with the term error matrix or confusion matrix. If not, don’t worry!

It is a way to measure if classification techniques work well, and it is quite appropriate in this case because under the hood, Dialogflow takes the user’s input and classifies it to the nearest matching intent.

So let us define the following terms:

Regular intent = An intent which is not a fallback intent

Correct mapping = the user’s phrase was mapped to the expected, appropriate intent. By the way, if you find the idea of “correct mapping” subjective rather than objective, you probably need to improve the way you are defining your intents.

True Positive (TP) = A user phrase is mapped to a regular intent correctly

True Negative (TN) = A user phrase is mapped to a fallback intent correctly (this means, we haven’t yet declared an intent to handle the user’s phrase)

False Positive (FP) = A regular intent is triggered, but it should have either been mapped to a different regular intent, or it should have been mapped to the fallback intent because we don’t yet handle the phrase. Instead it is wrongly mapped to a regular intent.

False Negative (FN) = A fallback intent is triggered, but we actually have already defined a regular intent which should have been mapped to the user’s phrase. An excellent example of this is when the user types a message which is nearly identical to a training phrase except for a small typo.

Sample size

Consider the last 100 user messages to your bot. If you don’t have that many, get some 10 or 15 beta testers to try out your bot for a few minutes.

Let TP be the number (out of the 100) messages which were true positive mappings.

Similarly, TN = number of true negative mappings

FP = number of false positive mappings

FN = number of false negative mappings

Let Correct Mapping (CM) = TP + TN

Let Incorrect Mapping (IM) = FP + FN

Accuracy = CM / CM + IM

Since CM + IM = 100 (if you got the correct sample size), the value is already a percentage.

Why measure the bot accuracy

If you are trying to improve your bot, a good way is to measure its accuracy using some objective measure [2]. By using the systematic approach I have explained here, you now have a numerical measure which can help.

[1] However, it works best with my existing recommendations such as avoiding slot filling, using a context lifespan of 1 etc. That makes the bot much easier to analyze.

[2] Although it isn’t the only one. A more useful measure might actually be how often the users accomplish their goals. Here Chatbase’s funnels feature is a lot more useful.

Similar Posts


  1. When a take a look to theIntent Detection Confidence, i see a score of 0.83768564. I suppose there is no way i know wich intent gets fired with the 0.16231436 score from the total of 1… as dialogflow dont display such an intent…

    1. Yes, that is correct. I wish Dialogflow would have implemented a top N intents feature. It is probably Dialogflow’s biggest shortcoming when compared to the other bot frameworks.