This is a lot less complicated than it appears. Given a set of sentences, each belonging to a class, and a new input sentence, we can count the occurrence of each word in each class, account for its commonality and assign each class a score. Factoring for commonality is important: matching the word “it” is considerably less meaningful than a match for the word “cheese”. The class with the highest score is the one most likely to belong to the input sentence. This is a slight oversimplification as words need to be reduced to their stems, but you get the basic idea.
"From Russia With Love" (PDF). Retrieved 2007-12-09. Psychologist and Scientific American: Mind contributing editor Robert Epstein reports how he was initially fooled by a chatterbot posing as an attractive girl in a personal ad he answered on a dating website. In the ad, the girl portrayed herself as being in Southern California and then soon revealed, in poor English, that she was actually in Russia. He became suspicious after a couple of months of email exchanges, sent her an email test of gibberish, and she still replied in general terms. The dating website is not named. Scientific American: Mind, October–November 2007, page 16–17, "From Russia With Love: How I got fooled (and somewhat humiliated) by a computer". Also available online.
In one particularly striking example of how this rather limited bot has made a major impact, U-Report sent a poll to users in Liberia about whether teachers were coercing students into sex in exchange for better grades. Approximately 86% of the 13,000 Liberian children U-Report polled responded that their teachers were engaged in this despicable practice, which resulted in a collaborative project between UNICEF and Liberia’s Minister of Education to put an end to it.
ELIZA's key method of operation (copied by chatbot designers ever since) involves the recognition of clue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses that can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY'). Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent".