AI unmasked: What is conversational AI

A huge number of travel related conversations is happening every day on social networks.

Based on nmodes Twitter data (averaged over 1.5 years of observations) there is

- 1 conversation every 15 minutes in which people notify that they are going to NYC;

- 1 conversation every 43 minutes in which people from the USA express intent to go to Europe;

- 1 conversation every 4 minutes with interest or intent to go on vacation;

- 1 conversation every 3 hours in which people are asking for hotel recommendations.

And this is just a tip of the iceberg.

(nmodes currently has 70+ travel-related topics and intents, and growing.)

For travel companies all these are qualified leads, potential customers, and attentive audience.

Reaching out to these potential customers results in a positive consumer experience, brand recognition, and, yes, sales!

Crowdsourced data can often be inconsistent, messy or downright wrong 

We all like something for nothing, that’s why open source software is so popular. (It’s also why the Pirate  Bay exists). But sometimes things that seem too good to be true are just that. 

Repustate is in the text analytics game which means we needs lots and lots of data to model certain  characteristics of written text. We need common words, grammar constructs, human-annotated corpora  of text etc. to make our various language models work as quickly and as well as they do. 

We recently embarked on the next phase of our text analytics adventure: semantic analysis. Semantic  analysis the process of taking arbitrary text and assigning meaning to the individual, relevant components.  For example, being able to identify “apple” as a fruit in the sentence “I went apple picking yesterday” but to  identify “Apple’ the company when saying “I can’t wait for the new Apple product announcement” (note:  even though I used title case for the latter example, casing should not matter)