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

Webservices and Robots: How can they help you ? Twitter Bots and Intelligent Agents

Hi folks,

During the free time (it doesn't happen often), I've worked on some projects including Twitter and Web Services. Those topics are extremely related to my current master thesis, which uses data source from social networks such as Twitter, Foursquare, Gowalla in order to monitor the behavior of the users and recommend new content, services or products based on their interest. Deliver this content means  the user receive information by web, mobile phones or through a specific interface.

One of my recent works is building Twitter robots. What's that ?!  WebServices that could be offered by the Twitter interface. For instance, imagine a service where you ask an information about a movie at Twitter through statuses updates, such as '@movieTheaters Iron man 2'.  The webservice receives this data (since you mentioned the @moviesTheaters) , parses, interpret it and as result deliver to the user the schedule of the theaters that play this movie close to the user's location or also the synopsis  of the movie, etc.

Why Twitter ?!  Twitter has been a sucessful player on this new generation of microblogs and social networks. Based on messages with 140 characters shared between users, nowadays the number of tweets (i.e. messages) have made nearly 13 billion. Yet, there's two unique things about the Twitter's content that makes it much valuable than any other public database of this size.

A Tweet has an author, a time and possibly hastags and @reply information that is all incredibly easy to access computationally. While web pages & blog posts also often have this information, it is much harder to access. For computers, there’s no simple way to respond to the author of most information on the web. Together these features lead to some very interesting possibilities for Twitter robots (bots).
 The structure of Twitter makes it relatively easy to extract the information contained in a Tweet- moreover, if it's a single question. ' Where can I find... ?' 'What's the best... ? ' , 'How much does ... cost'?  All those questions regularly appears in the Twitter stream. Building a Twitter bot that extract these Tweets & parses them for meaning within a specific field is extremely valuable. Thus, from the meta-data attached to a status update, a bot can easily answer to the author and reference the tweet is it replying too. The original author will pick up the response in their @replies or @directmessages (for privacy issues)  and see the link to the Tweet the response is to. Before presenting some examples, let's now talk about the robots. Its popular name is bots, which is an abbreviation for it.

Bots

Bots are intelligent agents that visit a number of search engines to identify information that matches a search profile provided by a user. There are a number of different kinds of bots designed to fulfil different purposes, such as software bots, stock bots, update bots, fun bots, chatter bots, and news bots. The possibilities for bots, specially on Twitter, is endless. Here I present two bots that I developed that demonstrate this concept.

TransitoRE

TransitoRe is a Twitter Bot that crawls the data provided from the many traffic cameras located along highways and streets throughout the city of Recife, Pernambuco - Brazil. The data is provided by the Recife Mayor Council and is updated every minute. Through the Twitter, the user now can obtain the real time traffic as also the location of the camera, since the Tweets come with the information about the traffic, name of the highway, images of the camera and even the geo coordinates where they are placed. It's a useful web service for the user that lives at Recife and wants to quickly gather information about the traffic in order to avoid this streets before going out. The service runs under the Google AppEngine and it'sa perfect example of how Twitter can help their users to obtain this information. The user just needs to follow the Twitter bot, and the  it will be responsible for post updates about the traffic in pre - defined intervals. It's important to notice that in this type of bot the user doesn't interact with it. It only delivers information, and is very popular in  deliver weather, stocks information.

TransitoRe : Twitter Bot

Tweetcomendas
 
This bot is another demonstration of a full operational bot that interacts with the user. Tweetcomendas was developed by me (marcelcaraciolo) and my friend (ricardocaspirro) and its design  by (lucianacns). It is a web service that runs through Twitter which the user can easily track his SEDEX shipments. SEDEX is a popular Express Courier Service, a division of Correios in Brazil. It is famous  for deliver all around Brazil  shipments and packages.

The difference of @tweetcomendas  to @transitoRE is that since the first uses direct messages, the user must follow it so it can send direct messages to him. The messages contain information from the web service at Correios, delivering the last status of the shipment at their system. The user just needs to send a reply to the system with the track code and it automatically starts to track his package by delivering real time information about it in accordance to the Correios Track System.  The bot now has a simply interaction with the user, demonstrating how this bots (robots) could deliver and talk with the user in order to deliver what he needs or based on his interests help him to discover new content.

Here are some screenshots of the web service:

Tweetcomendas bot

tweetcomendas web site

Those bots are all developed using free technologies with Python and Google App Engine. For you interested in get more details about those webservices and how we handled to develop it, post a comment at this blog! I will try to answer as soon as possible!

In conclusion, the possibilities for bots capitalising on this concept is endless. Bots that provide directions, restaurant or product recommendations, or weather information are just a few ideas. As Twitter grows the number of people a simple bot will reach continues to increase.

You can see a lot of other twitter bots here at this link. 

I expect you enjoyed this post!

See you next time,

Marcel Caraciolo