SlideShare a Scribd company logo
Smart Chat 
Rishi Dua 
Harvineet Singh 
Real-time chat-based personalized recommendation system 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 1 / 15
Smart Chat 
Motivation 
Combining Chat and Information 
Limited features of traditional chat systems 
No recommendations based on 
User interests and needs 
Schedule and planning 
No application of NLP techniques for unstructured text (chat) 
E-commerce websites: Amazon, Ebay etc. 
Based on viewed and purchased products 
More products suggested based on previous choice 
Personalisation with Privacy 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 2 / 15
Smart Chat 
Problem Statement 
Developing a chat application providing real time suggestions 
Movies: Show timings, recent movies 
Food: Restaurant reviews 
Products: Reviews, shopping links 
Travel to city: Train/
ight booking, Hotels, weather etc. 
Plans/Meetings: Calendar and personal schedule 
And so on..choice 
Recommendations improved with user interaction 
Learns preferences and interests 
Recommendations personalised with user feedback 
Tracking user clicks to improve classi
cation accuracy 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 3 / 15
Smart Chat 
Existing Work 
Applications developed 
GaChat: Returns information from Wikipedia relevant to users chat 
SemChat: Extracting Personal Information from Chat Conversations 
Current research 
Topic detection and extraction in chat 
Information extraction from chat corpus study 
Recommendations improved with user interaction 
Trained on
xed given corpus 
None of the research techniques give real-time recommendations 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 4 / 15
Smart Chat 
Approach 
Live Recommendation System 
User sentences categorised into prede
ned categories: food, cars, 
movies, travel etc. 
Using NLP,
gure out the topic of conversation 
Find relevant websites 
Using open source search APIs to
nd recommendations from given 
websites 
Users feedback used to improve future recommendations 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 5 / 15
Smart Chat 
User Interface 
Figure: Screenshot of the User Interface 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 6 / 15
Smart Chat 
Deciding when to give suggestion 
Figure: Recommendation is shown when 3 consecutive sentences are from same 
topic 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 7 / 15
Smart Chat 
Feedback from user to improve prediction 
Figure: Screenshot of the User Interface 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 8 / 15
Smart Chat 
Tracking user preference 
Figure: Ranking of recommendation gets updated when user clicks on a 
recommendation 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 9 / 15
Smart Chat 
Privacy 
Chat data saved anonymously in corpus 
Training on chat session instead of users chat history 
Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 10 / 15

More Related Content

Viewers also liked

ActivEngage Dealer Chat Real-Time Communication
ActivEngage Dealer Chat Real-Time CommunicationActivEngage Dealer Chat Real-Time Communication
ActivEngage Dealer Chat Real-Time Communication
360Converge, Inc.
 
Managing ejabberd Platforms with Docker - ejabberd Workshop #1
Managing ejabberd Platforms with Docker - ejabberd Workshop #1Managing ejabberd Platforms with Docker - ejabberd Workshop #1
Managing ejabberd Platforms with Docker - ejabberd Workshop #1
Mickaël Rémond
 
Zigbee based two way wireless chatting system
Zigbee based two way wireless chatting systemZigbee based two way wireless chatting system
Zigbee based two way wireless chatting system
Shashidhar Reddy
 
IoT時代を支えるプロトコルMQTT技術詳解
IoT時代を支えるプロトコルMQTT技術詳解IoT時代を支えるプロトコルMQTT技術詳解
IoT時代を支えるプロトコルMQTT技術詳解
Naoto MATSUMOTO
 
【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社
【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社
【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社
leverages_event
 
Zing Me Real Time Web Chat Architect
Zing Me Real Time Web Chat ArchitectZing Me Real Time Web Chat Architect
Zing Me Real Time Web Chat Architect
Chau Thanh
 
Real-time Chat Backend on AWS IoT 20160422
Real-time Chat Backend on AWS IoT 20160422Real-time Chat Backend on AWS IoT 20160422
Real-time Chat Backend on AWS IoT 20160422
akitsukada
 
Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...
Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...
Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...
Amazon Web Services
 
Zingme practice for building scalable website with PHP
Zingme practice for building scalable website with PHPZingme practice for building scalable website with PHP
Zingme practice for building scalable website with PHPChau Thanh
 
20150726 IoTってなに?ニフティクラウドmqttでやったこと
20150726 IoTってなに?ニフティクラウドmqttでやったこと20150726 IoTってなに?ニフティクラウドmqttでやったこと
20150726 IoTってなに?ニフティクラウドmqttでやったこと
Daichi Morifuji
 
Awsでつくるapache kafkaといろんな悩み
Awsでつくるapache kafkaといろんな悩みAwsでつくるapache kafkaといろんな悩み
Awsでつくるapache kafkaといろんな悩み
Keigo Suda
 
リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜
リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜 リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜
リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜
Yugo Shimizu
 
Low Latency Mobile Messaging using MQTT
Low Latency Mobile Messaging using MQTTLow Latency Mobile Messaging using MQTT
Low Latency Mobile Messaging using MQTT
Henrik Sjöstrand
 
Mqttで始めるIoT
Mqttで始めるIoTMqttで始めるIoT
Mqttで始めるIoT
Shintaro Hosoai
 
Develop a Messaging App on AWS in One Day
Develop a Messaging App on AWS in One DayDevelop a Messaging App on AWS in One Day
Develop a Messaging App on AWS in One Day
Amazon Web Services
 
AWS Real-Time Event Processing
AWS Real-Time Event ProcessingAWS Real-Time Event Processing
AWS Real-Time Event Processing
Amazon Web Services
 
Lan chat system
Lan chat systemLan chat system
Lan chat system
Wipro
 
Google Cloud Storage backup and archive
Google Cloud Storage backup and archiveGoogle Cloud Storage backup and archive
Google Cloud Storage backup and archive
Ido Green
 
A project report on chat application
A project report on chat applicationA project report on chat application
A project report on chat applicationKumar Gaurav
 

Viewers also liked (19)

ActivEngage Dealer Chat Real-Time Communication
ActivEngage Dealer Chat Real-Time CommunicationActivEngage Dealer Chat Real-Time Communication
ActivEngage Dealer Chat Real-Time Communication
 
Managing ejabberd Platforms with Docker - ejabberd Workshop #1
Managing ejabberd Platforms with Docker - ejabberd Workshop #1Managing ejabberd Platforms with Docker - ejabberd Workshop #1
Managing ejabberd Platforms with Docker - ejabberd Workshop #1
 
Zigbee based two way wireless chatting system
Zigbee based two way wireless chatting systemZigbee based two way wireless chatting system
Zigbee based two way wireless chatting system
 
IoT時代を支えるプロトコルMQTT技術詳解
IoT時代を支えるプロトコルMQTT技術詳解IoT時代を支えるプロトコルMQTT技術詳解
IoT時代を支えるプロトコルMQTT技術詳解
 
【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社
【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社
【 ITベンチャーを支えるテクノロジー 】チャットワークを支える技術|Chatwork株式会社
 
Zing Me Real Time Web Chat Architect
Zing Me Real Time Web Chat ArchitectZing Me Real Time Web Chat Architect
Zing Me Real Time Web Chat Architect
 
Real-time Chat Backend on AWS IoT 20160422
Real-time Chat Backend on AWS IoT 20160422Real-time Chat Backend on AWS IoT 20160422
Real-time Chat Backend on AWS IoT 20160422
 
Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...
Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...
Real-time Streaming and Querying with Amazon Kinesis and Amazon Elastic MapRe...
 
Zingme practice for building scalable website with PHP
Zingme practice for building scalable website with PHPZingme practice for building scalable website with PHP
Zingme practice for building scalable website with PHP
 
20150726 IoTってなに?ニフティクラウドmqttでやったこと
20150726 IoTってなに?ニフティクラウドmqttでやったこと20150726 IoTってなに?ニフティクラウドmqttでやったこと
20150726 IoTってなに?ニフティクラウドmqttでやったこと
 
Awsでつくるapache kafkaといろんな悩み
Awsでつくるapache kafkaといろんな悩みAwsでつくるapache kafkaといろんな悩み
Awsでつくるapache kafkaといろんな悩み
 
リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜
リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜 リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜
リアルタイムサーバー 〜Erlang/OTPで作るPubSubサーバー〜
 
Low Latency Mobile Messaging using MQTT
Low Latency Mobile Messaging using MQTTLow Latency Mobile Messaging using MQTT
Low Latency Mobile Messaging using MQTT
 
Mqttで始めるIoT
Mqttで始めるIoTMqttで始めるIoT
Mqttで始めるIoT
 
Develop a Messaging App on AWS in One Day
Develop a Messaging App on AWS in One DayDevelop a Messaging App on AWS in One Day
Develop a Messaging App on AWS in One Day
 
AWS Real-Time Event Processing
AWS Real-Time Event ProcessingAWS Real-Time Event Processing
AWS Real-Time Event Processing
 
Lan chat system
Lan chat systemLan chat system
Lan chat system
 
Google Cloud Storage backup and archive
Google Cloud Storage backup and archiveGoogle Cloud Storage backup and archive
Google Cloud Storage backup and archive
 
A project report on chat application
A project report on chat applicationA project report on chat application
A project report on chat application
 

Similar to Smart Chat

Final Presentation
Final PresentationFinal Presentation
Final PresentationBryan Then
 
Detection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
Detection and Analysis of Twitter Trending Topics via Link-Anomaly DetectionDetection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
Detection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
IJERA Editor
 
IRJET- Twitter Sentimental Analysis for Predicting Election Result using ...
IRJET-  	  Twitter Sentimental Analysis for Predicting Election Result using ...IRJET-  	  Twitter Sentimental Analysis for Predicting Election Result using ...
IRJET- Twitter Sentimental Analysis for Predicting Election Result using ...
IRJET Journal
 
lms final ppt.pptx
lms final ppt.pptxlms final ppt.pptx
lms final ppt.pptx
KratiAgarwal28
 
Integrated marketing 2014
Integrated marketing 2014Integrated marketing 2014
Integrated marketing 2014
Smart Insights
 
Interviews
InterviewsInterviews
Interviews
CIToolkit
 
Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...
Siwar Abidi
 
An Executives Guide to the Economics of SharePoint Development and the Cloud
An Executives Guide to the Economics of SharePoint Development and the CloudAn Executives Guide to the Economics of SharePoint Development and the Cloud
An Executives Guide to the Economics of SharePoint Development and the Cloud
Dan Barker
 
Recommendation System Using Social Networking
Recommendation System Using Social Networking Recommendation System Using Social Networking
Recommendation System Using Social Networking
ijcseit
 
Sentiment Analysis of Twitter tweets using supervised classification technique
Sentiment Analysis of Twitter tweets using supervised classification technique Sentiment Analysis of Twitter tweets using supervised classification technique
Sentiment Analysis of Twitter tweets using supervised classification technique
IJERA Editor
 
IRJET - Election Result Prediction using Sentiment Analysis
IRJET - Election Result Prediction using Sentiment AnalysisIRJET - Election Result Prediction using Sentiment Analysis
IRJET - Election Result Prediction using Sentiment Analysis
IRJET Journal
 
Movies recommendation system in R Studio, Machine learning
Movies recommendation system in  R Studio, Machine learning Movies recommendation system in  R Studio, Machine learning
Movies recommendation system in R Studio, Machine learning
Mauryasuraj98
 
Online social network analysis with machine learning techniques
Online social network analysis with machine learning techniquesOnline social network analysis with machine learning techniques
Online social network analysis with machine learning techniques
Hari KC
 
2.pdf
2.pdf2.pdf
2.pdf
mkhawaruol
 
Citihub Open Source and Cloud approach to Social Media Listening
Citihub Open Source and Cloud approach to Social Media ListeningCitihub Open Source and Cloud approach to Social Media Listening
Citihub Open Source and Cloud approach to Social Media Listening
Chris Allison
 
A Sentiment-Based Approach to Twitter User Recommendation
A Sentiment-Based Approach to Twitter User RecommendationA Sentiment-Based Approach to Twitter User Recommendation
A Sentiment-Based Approach to Twitter User RecommendationDavide Feltoni Gurini
 
The Value of Key Performance Indicators: Unlock Your Data
The Value of Key Performance Indicators: Unlock Your DataThe Value of Key Performance Indicators: Unlock Your Data
The Value of Key Performance Indicators: Unlock Your Data
Kathy McShea
 
A Frame-work for Efficient Education and Exam Preparations
A Frame-work for Efficient Education and Exam PreparationsA Frame-work for Efficient Education and Exam Preparations
A Frame-work for Efficient Education and Exam Preparations
Siddhant Kumar
 
Sentiment Analysis on Twitter data using Machine Learning
Sentiment Analysis on Twitter data using Machine LearningSentiment Analysis on Twitter data using Machine Learning
Sentiment Analysis on Twitter data using Machine Learning
IRJET Journal
 
Recommending content from social information streams
Recommending content from social information streamsRecommending content from social information streams
Recommending content from social information streams
PARC, a Xerox company
 

Similar to Smart Chat (20)

Final Presentation
Final PresentationFinal Presentation
Final Presentation
 
Detection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
Detection and Analysis of Twitter Trending Topics via Link-Anomaly DetectionDetection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
Detection and Analysis of Twitter Trending Topics via Link-Anomaly Detection
 
IRJET- Twitter Sentimental Analysis for Predicting Election Result using ...
IRJET-  	  Twitter Sentimental Analysis for Predicting Election Result using ...IRJET-  	  Twitter Sentimental Analysis for Predicting Election Result using ...
IRJET- Twitter Sentimental Analysis for Predicting Election Result using ...
 
lms final ppt.pptx
lms final ppt.pptxlms final ppt.pptx
lms final ppt.pptx
 
Integrated marketing 2014
Integrated marketing 2014Integrated marketing 2014
Integrated marketing 2014
 
Interviews
InterviewsInterviews
Interviews
 
Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...Recommender system and big data (design a smartphone recommender system based...
Recommender system and big data (design a smartphone recommender system based...
 
An Executives Guide to the Economics of SharePoint Development and the Cloud
An Executives Guide to the Economics of SharePoint Development and the CloudAn Executives Guide to the Economics of SharePoint Development and the Cloud
An Executives Guide to the Economics of SharePoint Development and the Cloud
 
Recommendation System Using Social Networking
Recommendation System Using Social Networking Recommendation System Using Social Networking
Recommendation System Using Social Networking
 
Sentiment Analysis of Twitter tweets using supervised classification technique
Sentiment Analysis of Twitter tweets using supervised classification technique Sentiment Analysis of Twitter tweets using supervised classification technique
Sentiment Analysis of Twitter tweets using supervised classification technique
 
IRJET - Election Result Prediction using Sentiment Analysis
IRJET - Election Result Prediction using Sentiment AnalysisIRJET - Election Result Prediction using Sentiment Analysis
IRJET - Election Result Prediction using Sentiment Analysis
 
Movies recommendation system in R Studio, Machine learning
Movies recommendation system in  R Studio, Machine learning Movies recommendation system in  R Studio, Machine learning
Movies recommendation system in R Studio, Machine learning
 
Online social network analysis with machine learning techniques
Online social network analysis with machine learning techniquesOnline social network analysis with machine learning techniques
Online social network analysis with machine learning techniques
 
2.pdf
2.pdf2.pdf
2.pdf
 
Citihub Open Source and Cloud approach to Social Media Listening
Citihub Open Source and Cloud approach to Social Media ListeningCitihub Open Source and Cloud approach to Social Media Listening
Citihub Open Source and Cloud approach to Social Media Listening
 
A Sentiment-Based Approach to Twitter User Recommendation
A Sentiment-Based Approach to Twitter User RecommendationA Sentiment-Based Approach to Twitter User Recommendation
A Sentiment-Based Approach to Twitter User Recommendation
 
The Value of Key Performance Indicators: Unlock Your Data
The Value of Key Performance Indicators: Unlock Your DataThe Value of Key Performance Indicators: Unlock Your Data
The Value of Key Performance Indicators: Unlock Your Data
 
A Frame-work for Efficient Education and Exam Preparations
A Frame-work for Efficient Education and Exam PreparationsA Frame-work for Efficient Education and Exam Preparations
A Frame-work for Efficient Education and Exam Preparations
 
Sentiment Analysis on Twitter data using Machine Learning
Sentiment Analysis on Twitter data using Machine LearningSentiment Analysis on Twitter data using Machine Learning
Sentiment Analysis on Twitter data using Machine Learning
 
Recommending content from social information streams
Recommending content from social information streamsRecommending content from social information streams
Recommending content from social information streams
 

Recently uploaded

Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
Adtran
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
Alex Pruden
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
Kari Kakkonen
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
KAMESHS29
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Paige Cruz
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
sonjaschweigert1
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 

Recently uploaded (20)

Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
Pushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 daysPushing the limits of ePRTC: 100ns holdover for 100 days
Pushing the limits of ePRTC: 100ns holdover for 100 days
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
 
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdfObservability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
Observability Concepts EVERY Developer Should Know -- DeveloperWeek Europe.pdf
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...A tale of scale & speed: How the US Navy is enabling software delivery from l...
A tale of scale & speed: How the US Navy is enabling software delivery from l...
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 

Smart Chat

  • 1. Smart Chat Rishi Dua Harvineet Singh Real-time chat-based personalized recommendation system Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 1 / 15
  • 2. Smart Chat Motivation Combining Chat and Information Limited features of traditional chat systems No recommendations based on User interests and needs Schedule and planning No application of NLP techniques for unstructured text (chat) E-commerce websites: Amazon, Ebay etc. Based on viewed and purchased products More products suggested based on previous choice Personalisation with Privacy Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 2 / 15
  • 3. Smart Chat Problem Statement Developing a chat application providing real time suggestions Movies: Show timings, recent movies Food: Restaurant reviews Products: Reviews, shopping links Travel to city: Train/ ight booking, Hotels, weather etc. Plans/Meetings: Calendar and personal schedule And so on..choice Recommendations improved with user interaction Learns preferences and interests Recommendations personalised with user feedback Tracking user clicks to improve classi
  • 4. cation accuracy Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 3 / 15
  • 5. Smart Chat Existing Work Applications developed GaChat: Returns information from Wikipedia relevant to users chat SemChat: Extracting Personal Information from Chat Conversations Current research Topic detection and extraction in chat Information extraction from chat corpus study Recommendations improved with user interaction Trained on
  • 6. xed given corpus None of the research techniques give real-time recommendations Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 4 / 15
  • 7. Smart Chat Approach Live Recommendation System User sentences categorised into prede
  • 8. ned categories: food, cars, movies, travel etc. Using NLP,
  • 9. gure out the topic of conversation Find relevant websites Using open source search APIs to
  • 10. nd recommendations from given websites Users feedback used to improve future recommendations Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 5 / 15
  • 11. Smart Chat User Interface Figure: Screenshot of the User Interface Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 6 / 15
  • 12. Smart Chat Deciding when to give suggestion Figure: Recommendation is shown when 3 consecutive sentences are from same topic Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 7 / 15
  • 13. Smart Chat Feedback from user to improve prediction Figure: Screenshot of the User Interface Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 8 / 15
  • 14. Smart Chat Tracking user preference Figure: Ranking of recommendation gets updated when user clicks on a recommendation Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 9 / 15
  • 15. Smart Chat Privacy Chat data saved anonymously in corpus Training on chat session instead of users chat history Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 10 / 15
  • 17. cation 1 Pre-processing: Stop words removal, Stemming using WorldNet lemmatizer 2 Feature extraction: TF-IDF of word count vectors 3 Feature selection: Select k-best features using Chi-square feature selection 4 Classi
  • 18. cation: Multinomial NB, Bernoulli, LinearSVC, Perceptron using scikit-learn library 5 Cross-validation: f-1 score to select best classi
  • 19. er Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 11 / 15
  • 20. Smart Chat Algorithm - Recommendations 1 Figure out the topic of conversation from learnt model 2 Mark chat as discussion if 3 consecutive sentences are from same topic 3 If chat is a discussion 1 Search for recommendations from given websites using open source search APIs 2 Track users clicks 3 On clicking a recommendation: Mark text as correctly classi
  • 21. ed and add to corpus Increase score of the recommended website for future recommendations 4 On clicking a feedback link 5 Mark text as incorrectly classi
  • 22. ed and add to marked corpus Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 12 / 15
  • 23. Smart Chat Results Selecting Algorithm Figure: Comparison of learning algorithms on our dataset Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 13 / 15
  • 24. Smart Chat Results Feature Selection Figure: K best features (Log scale) using Chi-Square measure Top: Linear SVM, middle: Multinomial, bottom: Bernoulli Multinomial outperforms Bernoulli for large vocabulary Good accuracy obtained on using 5000 words as features Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 14 / 15
  • 25. Smart Chat Future Scope Personalization of the feature extraction technique Clustering of users based on their preferences Maintaining an activity calendar to remind user of his schedule while planning tentative work on chat. Yet to implement the calendar feature in the application Changing from a Ajax based chat to an XMPP chat server Integrating with Facebook chat API Rishi Dua (IIT Delhi) Twitter Recommendation 28 May 2014 15 / 15