mini review on chatbots

1. Mini Review on Chatterbots
From ELIZA to Alexa and Beyond!
Summary
1. Introduction
2. Reviewing the field
3. Suggestions for further work
4. Implications
5. Conclusion
From Eliza to Alexa and Beyond 1

2. Introduction
The words people use in their daily lives in either verbal or written communication can reveal
important aspects of their social and psychological worlds. With advances in computer technology, text
analysis allows researchers to reliably and quickly assess features of what people say as well as
thoroughness in their linguistic styles. Following a brief review of several text analysis programs, a
computer can summarize some of the evidence that links natural word use to personality, social and
situational fluctuations, and psychological interventions. ​Natural Language Processing (NLP) is one
such area of computer science and artificial intelligence, that concerned with the interactions between
computers and human languages.
One of the applications of NLP is ​Chatbot- ​also known as a Talkbot, Chatterbot, Bot, IM Bot,
Interactive Agent, or Artificial Conversational Entity. A chatbot is a computer program that mimics
written or spoken human speech for the purposes of simulating a conversation with a real person.
Chatbots are typically used in dialog systems for various practical purposes including customer service or
information acquisition. Some chatterbots use sophisticated Natural Language Processing systems, the
same technology that forms the basis of the voice recognition systems used by virtual assistants such as
Google assistant, Apple’s Siri, and Microsoft’s Cortana, but many simpler systems scan for keywords
within the input, then pull a reply with the most matching keywords, or the most similar wording pattern,
from a database.
Chatbots process the text presented to
them by the user, before responding according to
a complex series of algorithms that identifies what
the user said, infers what they mean, and
determine a series of appropriate responses based
on this information. Although chatbot technology
is distinctly different from natural language
processing technology, without continued
developments in NLP, chatbots remain at the
mercy of algorithms’ current ability to detect the
subtle nuances in both written and spoken
dialogue.
From Eliza to Alexa and Beyond 2

3. There are two primary ways chatbots are offered to visitors:
● standalone apps
● web-based application
Today, most chatbots are either accessed via virtual assistants such as Google Assistant and
Amazon Alexa, via messaging apps such as Facebook Messenger or WeChat, or via individual
organizations' apps and websites. Chatbots can be classified into usage categories such as conversational
commerce, analytics, communication, customer support, design, developer tools, education,
entertainment, finance, food, games, health, HR, marketing, news, personal, productivity, shopping,
social, sports, travel, and utilities.
ELIZA an early natural language processing computer program and the first chatbot ever
coded ​was invented in 1966 at the MIT Artificial Intelligence Laboratory by Joseph Weizenbaum, using
only 200 lines of code! ​ELIZA imitate the language of a therapist. Eliza simulated conversation by using
a 'pattern matching' and substitution methodology that gave users an illusion of understanding on the part
of the program, but had no built-in framework for contextualizing events. ​
Directives on how to interact
were provided by 'scripts', written originally in MAD-Slip, which allowed ELIZA to process. ​Using
almost no information about human thought or emotion, it sometimes provided a startlingly human-like
interaction. For example, ELIZA responding to "My head hurts" with "Why do you say your head hurts?".
In this mini-review we will discuss more on the history and development of chatbots, the
invention of the first chatbot ever who can pass the Turing Test- ELIZA, their real-life applications, and
future scope.
From Eliza to Alexa and Beyond 3

4. Reviewing the Field
“ ELIZA A Computer Program For the Study of Natural Language
Communication Between Man And Machine ”
ELIZA name was chosen to emphasize that it may be incrementally improved by its users, since
its language abilities may be continually improved by a "teacher".
The ​MAC System ​is one which permits an individual to operate a full seale computer from a
remotely located typewriter. The individual operator has the illusion that, he is the sole user of the
computer, while in fact others may be "time-sharing" the system with him. What is important here is that
the computer can read messages typed on the typewriter and respond by writing on the same instrument.
The time between the computer's receipt of a message and the appearance of its response is a function of
the program controlling the dialogue and of such MAC system parameters as the number of users currently
corresponding with the system.
Is she a rogerian Psychotherapist, a semi intelligent Chatbot, or just a Toy?
When in conversation with ELIZA, the user types in some statement or set of statements in natural
language using normal punctuation and sentence structures. Only the question mark may not be used,
because it is interpreted as a line delete character by the MAC system. The user's statement is terminated
by a double carriage return (enter key) which serves to turn control over to ELIZA. ELIZA then analyzes
the user's statement and generates some response which it types out. Control is then again with the user.
Basic principle of ELIZA: Input sentences are analyzed on the basis of decomposition rules which are
triggered by key words appearing in the input text. Responses are generated by reassembly rules
associated with selected decomposition rules.
Script: Keywords and their associated transformation rules constitute the SCRIPT for a particular class of
conversation.
Transformation Rules:
● Decompose a data string according to certain criteria, hence to test the string as to whether it
satisfies these criteria or not.
● Reassemble a decomposed string according to certain assembly specifications.
From Eliza to Alexa and Beyond 4

5. A translation table used to convert things human say into things the ELIZA says back,
"I am" ​→ ​ "you are"
am are
was were
i you
i’d you would
i’ve you have
i’ll you will
my your
are am
you've I have
you'll I will
your my
yours mine
you me
me you
The procedure of the program to generate above output:
● Read the text
● Inspect for the presence of a keyword
○ If keyword found, a sentence is transformed according to a Rule associated with the
keyword
If the sentence has “​I feel​” anywhere in the
sentence them output from ELIZA would be one
of the below sentence.
If sentence has word “​mother​” in it, then the
output will be one of these sentences.
]
If the input is word “​quit​”, then the output will be
one of these sentences.
If sentence has word “​because​” in it, then the
output will be one of these sentences.
Here, “%1” represent the rank of word after applying decomposition rule. See the second example given on
page no- 7 to know more. Similarly for many other keywords, ELIZA has hard coded sentences and the
output generated will be based on the choice of keyword and sentence.
From Eliza to Alexa and Beyond 5

6. ○ If keyword not found, an earlier transformation is retrieved or one of the following
sentences will be displayed
● Compute and Print the text
In detail, the procedure mentioned above is considerably more complex. Keywords may have a
RANK or precedence number associated with it. Thus, reading text from left-to-right, if more then one
keywords are found, the rightmost keyword will be considered by ELIZA if it has higher RANK as
compare to the left one.
What if the sentence has two phrases in it separated by a comma?
Here, comma or a period will also be considered as delimiter. So, if any one of it is encoundered,
and a keyword is already been found, all the remaining text to the right is discarded from the input
message. If no keyword is found yet, the sentence to the left of delimiter is discarded and the right half is
now checked. As a result, only single phrase or sentences are transformed.
From Eliza to Alexa and Beyond 6

7. The fundamental technical problems with which ELIZA must be preoccupied are the following:
1. The identification of the "most important" keyword occurring in the input message.
2. Tile identification of some minimal context within which the chosen keyword appears; e.g., if the
keyword is "you", is it followed by the word "are" (in which ease an assertion is probably being
made).
3. The choice of an appropriate transformation rule and, of course, the making of the transformation
itself.
4. The provision of mechanism that will permit ELIZA to respond "intelligently" when the input
text contained no keywords.
5. The provision of machinery that facilitates editing, particularly extension, of the script on the
script writing level.
A somewhat more complicated example:
From Eliza to Alexa and Beyond 7

8. What can we learn from ELIZA?
● The biggest learning point to get from ELIZA is about complexity. It amazes me how simple
ELIZA's script actually is, yet plenty of humans got easily tricked.
● Granted, this was a long time ago. In fact, this was 30 years before smartphones even reached our
pockets. This, once again, reinforces how much of an innovation ELIZA was.
● Yet, this is something you can take from this old chatbot: don't over complicate things. Sure, ELIZA
wasn't a smart chatbot by any means. It didn't learn or adapt. But it had one job to do and it did it
well.
Following is a brief description of chatbots developed after ELIZA:
Jabberwacky
● The chatbot was created by developer Rollo Carpenter in 1988. It aimed to simulate a natural human
conversation in an entertaining way.
● Jabberwacky has led to other technological growth. Some individuals use it for academic research
purposes through its webpage since its origin.
● The chatbot is considered to use an AI technique called “contextual pattern matching.”
Dr. Sbaitso
● Dr. Sbaitso is a chabot created by Creative Labs for MS-Dos in 1992.
● It is one of the earliest efforts of incorporating A.I. into a chatbot and is recognized for its full voice
operated chat program.
● The program would converse with the user as if it was a psychologist. Most of its responses were
along the lines of “Why do you feel that way?” rather than any sort of complicated interaction.
A.L.I.C.E. (Artificial Linguistic Internet Computer Entity)
● A.L.I.C.E. is a universal language processing chatbot that uses heuristic pattern matching to carry
conversations.
● The program works with the XML schema known as artificial intelligence markup language
(AIML), which helps specify conversation rules. In 1998, the program was edited in Java, and in
2001 Wallace printed an AIML specification.
● From there, other developers drafted free and open sources of ALICE in different programming
languages and a variety of foreign languages.
From Eliza to Alexa and Beyond 8

9. ● The program simulates chatting with a real person over the Internet. Alice is a young-looking
woman in human years and tells a user her age, hobbies and other fascinating facts, as well as
answering to the user’s dialog.
SmarterChild
● The SmartChild was in many ways a precursor of Siri and was developed in 2001.
● The chatbot was available on AOL IM and MSN Messenger with the strength to carry out fun
conversations with quick data access to other services.
● It suites Microsoft also built its own SmarterChild, years later after most people stopped using AIM
which targeted 18- to 24-year-olds in the U.S. the account suites particular conversation
Siri
● Siri was formed by Apple for iOS in 2010; it is an intelligent personal assistant and learning
navigator that uses a natural language UI. It paved the system for all AI bots and PAs after that.
● Similar to other texting and Facebook Messenger Apple’s patent describes a Siri that could perform
current duties without the user having to chat aloud. That could be helpful in several public spheres.
● They could reply to a text, audio, images, and video when transferred to it by the user.
From Eliza to Alexa and Beyond 9

10. Google Now
● Google Now was launched at Google Inc. in 2012. It answers questions, performs actions through
requests made to a set of web services and makes recommendations.
● Google Now was initially a way to get contextually appropriate information based on location and
time of the day. It evolved to become much more complicated and elaborate, with a broad range of
content categories delivered on cards.
● Sometimes it refers to us as predictive search. Currently, it’s built for use in smartphone and has
been upgraded to accommodate several features.
Cortana
● Cortana was first demonstrated at Microsoft’s Build 2014 developer conference, and it became
directly integrated into both Windows phone devices and Windows 10 PCs.
● This program uses voice recognition and relevant algorithms to get and respond to voice commands.
● Cortana can perform tasks like reminders based on time, places, or people, send emails and texts,
create and manage lists, chit-chat, and play games, find facts, files, locations, and info among others.
Alexa
● Alexa is an intelligent personal assistant developed by Amazon. It was introduced in 2014 and is
now built in to devices such as the Amazon Echo, the Echo Dot, the Echo Show and more.
● There is also an Alexa app and more devices from third-party manufacturers that have Alexa built in
to them.
● All you have to do is say “Alexa, play some music” or “Alexa, find me an Italian restaurant” and she
will help you out.
● Using nothing but the sound of your voice, you can search the Web, play music, create to-do or
shopping lists, set alarms, stream podcasts, play audiobooks, get news or weather reports, control
your smart-home products and more.
From Eliza to Alexa and Beyond 10

11. Suggestions for Future Work
Worldwide, we send over 23 billion text messages a day. Texting is the most widely used mode on
smartphones and over 90% of the text messages are read in under 3 minutes. Whatsapp, the most popular
messaging app reported that they are now handling over 30 billion messages daily. Shocking!
Consider ordering a pizza — traditionally done by calling the restaurant and verbally order over
phone; which is labor intensive, replaced with apps — which are time consuming in nature for order
processing. Enter chatbots; which combines the best of both the worlds fast, convenient way to place an
order while still having a conversation at front end while order ready is done at back-end.
What’s the predictive future of Chatbots?
1. Advances in AI development will impact Chatbots
2. Voice Experiences Going Mainstream
3. Blockchain the Surprising Ally for Chatbot
4. Social Messenger Applications will aggressively drive Chatbot Marketing
5. Chat Bots influence on Customer Insights will grow, predictability of user actions will increase.
6. Reach of Deep Learning and Artificial Intelligence will increase across all domains from 2018
7. Cost of Chatbots will get cheaper as the adoption of it increases across domains
Marketing in the 2000s was dominated by Search Engine Marketing and Optimization (SEM and
SEO). The early 2010s saw the rise of Facebook and social media marketing. Most recently we’ve seen
mobile marketing rise and plateau as users have stopped downloading new apps. Today, it’s all about
messaging. Consumer behavior has shifted from social networks to messaging platforms such as SMS,
Facebook Messenger, Apple iMessage, Slack, and WeChat.
To achieve this progress, the first step would be to accumulate an enormous amount of data, which
can be altered constantly. The biggest challenge for chatbots is mimicking real life conversations between
humans in the most convincing way. By using accumulated data, chatbots can be made to replicate a human
communication and embrace better personalisation.
With most users hitting their saturation point after constantly using a lot of apps on a daily basis, we
might see a better collaboration and co-existence of chatbots and apps in the future. Chatbots definitely have
made a special mark in the enterprise world, but did we truly tap their full potential? Only time will
answer…
From Eliza to Alexa and Beyond 11

12. Implications
The ELIZA effect ​refers only to “the susceptibility of people to read far more understanding than is
warranted into strings of symbols- especially words- strung together by computers”. More generally, the
ELIZA effect describes any situation where, based solely on a system's output, users perceive computer
systems as having “intrinsic qualities and abilities which the software controlling the output cannot possibly
achieve” or “assume that outputs reflect a greater causality than they actually do.”
A trivial example of the specific form of the Eliza effect, given by Douglas Hofstadter, involves an
automated teller machine which displays the words "THANK YOU" at the end of a transaction. A very
casual observer might think that the machine is actually expressing gratitude; however, the machine is only
printing a preprogrammed string of symbols!
From a psychological standpoint, the ELIZA effect is the result of a subtle cognitive dissonance
between the user's awareness of programming limitations and their behavior towards the output of the
program. The discovery of the ELIZA effect was an important development in artificial intelligence,
demonstrating the principle of using social engineering rather than explicit programming to pass a Turing
test.
Lay responses to ELIZA were disturbing to Weizenbaum and motivated him to write his book
Computer Power and Human Reason: From Judgment to Calculation​, in which he explains the limits of
computers, as he wants to make clear in people's minds his opinion that the anthropomorphic views of
computers are just a reduction of the human being and any life form for that matter. In the independent
documentary film Plug & Pray Weizenbaum said that only people who misunderstood ELIZA called it a
sensation.
ELIZA influenced a number of early computer games by demonstrating additional kinds of interface
designs. Don Daglow wrote an enhanced version of the program called Ecala on a DEC PDP-10
minicomputer at Pomona College in 1973 before writing the computer role-playing game, Dungeon.
From Eliza to Alexa and Beyond 12

13. Conclusion
Though the invention of bots took long back in 1966, it has only got recognition now by the world of
technology. Bots are still in their early stages but the momentum is picking up and advancements in the field
of artificial intelligence will definitely keep refining the bot experience for its users. Also one major reason
for rise in bots is because it is easier and cheaper to make when compared to apps.
Most bots in India are still on their way to achieve full automation. They are yet dependent on
humans when it comes to handling complex or detailed queries. But with the progressions taking place in the
fields of Natural Language Processing and artificial intelligence, it is not too far when bots will be fully
automated.
ELIZA has been referenced in popular culture and continues to be a source of inspiration for
programmers and developers focused on Artificial Intelligence. It was also featured in a 2012 exhibit at
Harvard University titled "Go Ask A.L.I.C.E", as part of a celebration of mathematician Alan Turing's 100th
birthday. The exhibit explores Turing's lifelong fascination with the interaction between humans and
computers, pointing to ELIZA as one of the earliest realizations of Turing's ideas.
“I had not realized...
that extremely short exposures to a relatively
simple computer program
could induce powerful delusional thinking
in quite normal people.”
- Joseph Weizenbaum
From Eliza to Alexa and Beyond 13

14. References
Journal Paper:
● Weizenbaum, J. (1966). ELIZA—a computer program for the study of natural language
communication between man and machine. Communications of the ACM, 9(1), 36-45.
Websites:
● https://chatbotsmagazine.com/
● https://chatbotslife.com
● https://en.wikipedia.org/wiki/Natural-language_processing
● https://en.wikipedia.org/wiki/Chatbot
● https://en.wikipedia.org/wiki/ELIZA
Date: April 02, 2018
Subject: Psychology
Submitted by: Charmi Chokshi
Roll No: 201501021
Guided by: Dr. Sumitava Mukherjee
School: School of Engineering and Applied Science, Ahmedabad University
From Eliza to Alexa and Beyond 14