My new experiment: TweetTalk : A Twitter Post Chatter ;D Update tweets from your Google Talk Account!

Hi all,

During my recent studies about Chatter Bots, I've inspired myself to build a new one now integrating Twitter and Google Talk IM Service.  His name is  TweetTalk.  What's the catch ?  

TweetTalk is a Jabber IM Bot for anyone who wants to quickly update a post on your Twitter Account. So instead of going to a separated client, directly from anywhere you can access the Google Talk Engine (Web mail or Desktop Client) you can just write your tweet and the bot will responsible of sending the post to the Twitter.

Let's see it in action:

The tweet status on Twitter:

As you can see, it is really fast now for me to send a tweet from my webmail gmail. It is a simple experiment of how those type of bots can improve your life and work daily.

If you wanna try it, please add to your contacts:   tweettalk@bot.im  

By the way I am using Python for developing the main logic of the Bot.  For web communication I used Django + Google AppEngine + Twitter API.  And as the bot infra-structure the Imified API.

I am writing some new articles about performance evaluation, recommendation engines, REST APIs and SVM with Keyword/Term Extraction. 

Stay tuned !

Marcel Caraciolo

Chatterbots and Natural Language Processing: A real example with Brazilian Correios Bot TweetComendas

Hi all,

In a previous post at this blog I've presented two web robots that I developed : Tweetcomendas and TransitoRE.  For Tweetcomendas, which is a Twitter bot for track mail orders from Brazilian post office Correios, I've developed a chat bot to interact with the users. Besides Twitter,  the user  also can track his orders by asking at real-time our Chat Client TweetComendas.

Recently, several approaches were proposed in the research domain of chatterbots. But first let's review the concepts of a chatterbot or chatbot.  Chatterbots are computer programs that seek to simulate a human in the conversation with other people. Its goal is to answer questions in a manner that people have the impression they are talking with a real person and not a computer program. This  tatement remembers me the Turing Test which is a test proposed by Alan Turing in his 1950 paper in order to evaluate the machine's ability to demonstrate intelligence by using conversation between humans and machines. It's quite interesting, I recommend the reading.

So after the dispatch of the questions in natural language, the program consults a knowledge database and then provides an answer which tries to mimic the human behavior.  Although, many chatterbots do appear to simulate the human input intelligently in their responses,  the bot that I developed tries to simulate an human assistant by scanning for keywords within the input and answers the closest as possible in natural language the statuses of the orders at Brazilian Correios.

Recently, chatbot techniques have been used for several practical purposes such as online help, personalised services or information acquisition, by working as a conversational agent. One of the classical examples of Chatterbot is A.L.I.C.E, which uses a weak A.I.. In the example of A.L.I.C.E, it uses a programming language called AIML, which is specific to its function as a conversational agent and has been adopted by many developers, which created the called Alicebots.

A.L.I.C.E

The one that I've liked a lot and at some way inspired to develop my own bot was the Aadvark ChatterBot. Aadvark, recently bought by Google, was  a startup focused on creating a social recommendation engine mashing-up some components of Yahoo! Answers and Instant Messaging.  Their service is to offer the user the possibility of asking a question to the bot, and based on its algorithms it will compute its own tag (keywords or you could give it a few) and then, it will find a right person to your question and it will forward it to him in order to  answer. The best part is that Aadvark works very well not only in their web page but also in another clients such as IM's, Iphone, etc.  So you have a question, just open the chat screen of the bot and ask a question and after some minutes you may get a useful answer in the same session (client). Try it for free and see its power!

Aadvark Chat Client

The Tweetcomendas ChatterBot is actually a Jabber Chat Clients which uses the XMPP protocol for receiving and pushing text messages. I've used as an example of another bots that I am planning to develop. Let's see a working example of how it works:

1- First, we have to add the chatter bot tweetcomendas@bot.im (it uses the IMIFIED IM's  bots infrastructure, so you can host your bot there for free.).

2 - After he comes online, you can send at anytime the tracking code of your package order from Correios in order to track it.

It uses regular expressions to match the tracking code.

3 - Wait while he looks at the Correios Tracking WebServices and receive the current status.

The current status in natural language for the user.

3 - Now, another useful feature of the Tweetcomendas ChatterBot is he can actually track for you automatically your order and any new updates he will come to you by giving the new status on your chat client if you're online or by sending you an e-mail (It only works with gmail by now.)

He will ask you politely if you want him to track your order for you.

A gentleman chatterBot :D

4 - Receive new updates of your order by e-mail or by your Jabber Client.

Updates on your e-mail even when you 're not online at the Google Talk

So, this is my first attempt to develop real useful chatter bots for helping users in order to track their post orders. There are many ideas in my mind that I want to create. I believe this kind of tool is the next generation of agents for interacting with people working as an assistant such as the Siri: a mobile assistant agent running on Iphones.  Take a look at the video and see the future of those kind of technologies.





I expect that you have enjoyed my simple bot, it still sometimes can be lazy but in almost of the time it works smoothly. Add to your Google Talk Contacts:  tweetcomendas@bot.im   This is a personal experiment project that I've developed with the help of Ricardo Caspirro (@ricardocaspirro) on intelligent agents and bots.  If you want more information  about it, take a look at its homepage. There is also other client working on Twitter!


That's all,

Cheers,

Marcel Caraciolo