SlideShare a Scribd company logo
Real-time Issue Data Analysis Using TextRank Algorithm
I N T R O D U C E M Y S E L F
JADE YEOM;
Software Engineer & UX/UI Designer
1999.11.21 



“EXPERIMENT, FAIL, LEARN, REPEAT.”
Education


February, 2018 - 14 

1 

February, 2015 -
Careers


April, 2016 - Founder



March, 2016 ~ April, 2017 - Software Engineer

Awards
30 

Oct, 2013 - (SchoolSOS)

31 

October, 2014 - (QuickTask)

SKPlanet Smarteen App Challenge 2015

August, 2015 - ( do:learn)

2016 UNIST 

August, 2016 - 

8 

July, 2017 - ( )
E X P E R I M E N T,
F A I L ,
L E A R N ,
R E P E AT.
1
P R O B L E M S A N D R E S E A R C H M E T H O D S
P R O B L E M S A N D R E S E A R C H M E T H O D S
1 500
  .
P R O B L E M S A N D R E S E A R C H M E T H O D S
?
P R O B L E M S A N D R E S E A R C H M E T H O D S
?
* 2014
P R O B L E M S A N D R E S E A R C H M E T H O D S
, .
?
P R O B L E M S A N D R E S E A R C H M E T H O D S
!
P R O B L E M S A N D R E S E A R C H M E T H O D S
1 2 3
2
PA G E R A N K A L G O R I T H M
(Vertex) ,
(Edge) (In graph theory)
A
0.25
B
0.25
C
0.25
D
0.25
PA G E R A N K A L G O R I T H M
A-D / B-C,D / C-B,D / D-A,B,C
.
A D 0.25
B C, D 0.125
C B, D 0.125
D A, B, C 0.08333
( )
PA G E R A N K A L G O R I T H M
A
0.083
B
0.208
C D
0.50.208
A-D / B-C,D / C-B,D / D-A,B,C
.
A D 0.25
B C, D 0.125
C B, D 0.125
D A, B, C 0.08333
( )
T E X T R A N K A L G O R I T H M
A
0.083
B
0.208
C D
0.50.208
, .
,
.
TextRank: Bringing Order into Texts Rada Mihalcea and Paul Tarau
3
T E X T R A N K A L G O R I T H M
(Schema)
T E X T R A N K A L G O R I T H M
30
4
T E X T R A N K A L G O R I T H M
7 1,000 7 KSCY 20
21 .
, , 1,000
. (
, ) ( , 2 ) /
, , .
20
. KSCY
, , , , - , Global
Session 9 30 .
.
, , 1
11 (www.kscy.kr) . KSCY
, ,
.
9 (Sentence)
211 (Noun) .
T E X T R A N K A L G O R I T H M
, ,
1 11
(www.kscy.kr) .
B
, , 1,000
.
A SENTENCE SENTENCE
, , , , , , , ,
, , , , , , , , ,
, , , , ,
A NOUNS
, , , , , , , ,
, , , , , , , , , ,
, , , ,
B NOUNS
?
!
T E X T R A N K A L G O R I T H M
*
(Cosine Similarity)
(Structural Equivalence)
T E X T R A N K A L G O R I T H M
T E X T R A N K A L G O R I T H M
T E X T R A N K A L G O R I T H M
, ,
1,000
.
A SENTENCE
, ,
1 11
(www.KSCY.kr) .
B SENTENCE
0.60000
.
TR
3
, , 1,000
0.16804301901203098
4
( , ) ( , 2 ) /
, ,
0.12720921437593927
2 7 KSCY 20 21 . 0.12403895720955871
8
, , 1 11
(www.KSCY.kr) .
0.12161567732116019
9
KSCY ,
,
0.11094304196222915
5
KSCY , , , , - , Global Session
9 30
0.09781542856211028
5
20
0.09671097626842523
7 0.08109264598251792
1 7 1,000 0.07253103930602833
T E X T R A N K A L G O R I T H M
7 1,000 7 KSCY 20
21 .
, , 1,000
. (
, ) ( , 2 ) /
, , .
20
. KSCY
, , , , - , Global
Session 9 30 .
.
, , 1
11 (www.KSCY.kr) . KSCY
, ,
.
30%
7 KSCY 20 21
.
, , 1,000
. (
, ) ( ,
2 ) / , ,
.
30%
T E X T R A N K A L G O R I T H M
T E X T R A N K A L G O R I T H M
,
.
' '
.
10 SNS  "
# # "
.
.
.
(11 ) ' ' 1 6
vs MVP,  8  vs 
.
T E X T R A N K A L G O R I T H M
TR
2 10 SNS " # # "
, , , , , , ,
, , ,
0.3644289912306943
1 ' ' .
, , , , ,
, , , ,
0.17644170069290174
3 .
, , , , , , ,
0.17348340763075204
5 (11 ) ' ' 1 6 vs MVP,  8  vs 
, , , , , ,
, , , ,
,
0.1446443616177518
4 , , , , , , 0.14100153882790015
/
(Jaccard Transformed Index For Specific Union)
T E X T R A N K A L G O R I T H M
' '
.
A SENTENCE
(11 ) ' ' 1 6 vs MVP,  8 
vs 
B SENTENCE
0.04347826 0.13043478
T E X T R A N K A L G O R I T H M
TR
5 (11 ) ' ' 1 6 vs MVP,  8  vs 
, , , , , ,
, , , , ,
, ,
0.36405889831533783
1 ' ' .
, , , , ,
, , , ,
0.20943504244072794
4
, , , , , , ,
0.14793614614904468
3
, , , , , ,
, , , ,
,
0.14014931482237628
2 10 SNS  " # # " . , , , , , , 0.13842059827251335
“ 5 .
HQ
.”
“
1 .”
“ 5
.”
1.
“ 5
, 1 .”
2.
T E X T R A N K A L G O R I T H M
“ 5 , 1
.
.”
3.
.
T E X T R A N K A L G O R I T H M
4.
,
.
keyword summary_issue started_at ended_at rank_avg
.
.
2017-07-10
16:19:14
2017-07-10
20:32:30
3.8
.
.
' '
.
2017-07-10
14:18:41
2017-07-10
16:19:00
2.4
2015
.
.
2017-07-10
08:18:41
2017-07-10
10:12:30
5.3
T E X T R A N K A L G O R I T H M
5
R E S U LT S
F U T U R E R E S E A R C H A N D E X P E C T E D E F F E C T S
.
https://rankr.kr
https://github.com/endlessdev/summarizer
F U T U R E R E S E A R C H A N D E X P E C T E D E F F E C T S
Real-time Issue Data Analysis Using TextRank Algorithm
Real-time Issue Data Analysis Using TextRank Algorithm
THANK YOU
FOR ATTENTION.

More Related Content

What's hot

Node.js Event Emitter
Node.js Event EmitterNode.js Event Emitter
Node.js Event Emitter
Eyal Vardi
 
Centralized log-management-with-elastic-stack
Centralized log-management-with-elastic-stackCentralized log-management-with-elastic-stack
Centralized log-management-with-elastic-stack
Rich Lee
 
Building Next-Generation Web APIs with JSON-LD and Hydra
Building Next-Generation Web APIs with JSON-LD and HydraBuilding Next-Generation Web APIs with JSON-LD and Hydra
Building Next-Generation Web APIs with JSON-LD and Hydra
Markus Lanthaler
 
Python on AWS Lambda
Python on AWS Lambda Python on AWS Lambda
Python on AWS Lambda
Amazon Web Services
 
Event Sourcing with Kotlin, who needs frameworks!
Event Sourcing with Kotlin, who needs frameworks!Event Sourcing with Kotlin, who needs frameworks!
Event Sourcing with Kotlin, who needs frameworks!
Nico Krijnen
 
Deep Dive Into Elasticsearch
Deep Dive Into ElasticsearchDeep Dive Into Elasticsearch
Deep Dive Into Elasticsearch
Knoldus Inc.
 
닷넷프레임워크에서 Redis 사용하기
닷넷프레임워크에서 Redis 사용하기닷넷프레임워크에서 Redis 사용하기
닷넷프레임워크에서 Redis 사용하기흥배 최
 
Elastic stack Presentation
Elastic stack PresentationElastic stack Presentation
Elastic stack Presentation
Amr Alaa Yassen
 
Sequelize
SequelizeSequelize
Sequelize
Tarek Raihan
 
Kafka monitoring using Prometheus and Grafana
Kafka monitoring using Prometheus and GrafanaKafka monitoring using Prometheus and Grafana
Kafka monitoring using Prometheus and Grafana
wonyong hwang
 
A History of PHP
A History of PHPA History of PHP
A History of PHP
Xinchen Hui
 
Elasticsearch development case
Elasticsearch development caseElasticsearch development case
Elasticsearch development case
일규 최
 
안정적인 서비스 운영 2014.03
안정적인 서비스 운영   2014.03안정적인 서비스 운영   2014.03
안정적인 서비스 운영 2014.03
Changyol BAEK
 
Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기
Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기
Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기
흥래 김
 
Deep Dive on Amazon DynamoDB
Deep Dive on Amazon DynamoDB Deep Dive on Amazon DynamoDB
Deep Dive on Amazon DynamoDB
Amazon Web Services
 
[236] 카카오의데이터파이프라인 윤도영
[236] 카카오의데이터파이프라인 윤도영[236] 카카오의데이터파이프라인 윤도영
[236] 카카오의데이터파이프라인 윤도영
NAVER D2
 
Building a Moodle theme with bootstrap
Building a Moodle theme with bootstrapBuilding a Moodle theme with bootstrap
Building a Moodle theme with bootstrap
Bas Brands
 
Build RESTful API Using Express JS
Build RESTful API Using Express JSBuild RESTful API Using Express JS
Build RESTful API Using Express JS
Cakra Danu Sedayu
 
Advanced angular
Advanced angularAdvanced angular
Advanced angular
Sumit Kumar Rakshit
 
AWSKRUG-33번째-세션1.pdf
AWSKRUG-33번째-세션1.pdfAWSKRUG-33번째-세션1.pdf
AWSKRUG-33번째-세션1.pdf
SeoyulYoon
 

What's hot (20)

Node.js Event Emitter
Node.js Event EmitterNode.js Event Emitter
Node.js Event Emitter
 
Centralized log-management-with-elastic-stack
Centralized log-management-with-elastic-stackCentralized log-management-with-elastic-stack
Centralized log-management-with-elastic-stack
 
Building Next-Generation Web APIs with JSON-LD and Hydra
Building Next-Generation Web APIs with JSON-LD and HydraBuilding Next-Generation Web APIs with JSON-LD and Hydra
Building Next-Generation Web APIs with JSON-LD and Hydra
 
Python on AWS Lambda
Python on AWS Lambda Python on AWS Lambda
Python on AWS Lambda
 
Event Sourcing with Kotlin, who needs frameworks!
Event Sourcing with Kotlin, who needs frameworks!Event Sourcing with Kotlin, who needs frameworks!
Event Sourcing with Kotlin, who needs frameworks!
 
Deep Dive Into Elasticsearch
Deep Dive Into ElasticsearchDeep Dive Into Elasticsearch
Deep Dive Into Elasticsearch
 
닷넷프레임워크에서 Redis 사용하기
닷넷프레임워크에서 Redis 사용하기닷넷프레임워크에서 Redis 사용하기
닷넷프레임워크에서 Redis 사용하기
 
Elastic stack Presentation
Elastic stack PresentationElastic stack Presentation
Elastic stack Presentation
 
Sequelize
SequelizeSequelize
Sequelize
 
Kafka monitoring using Prometheus and Grafana
Kafka monitoring using Prometheus and GrafanaKafka monitoring using Prometheus and Grafana
Kafka monitoring using Prometheus and Grafana
 
A History of PHP
A History of PHPA History of PHP
A History of PHP
 
Elasticsearch development case
Elasticsearch development caseElasticsearch development case
Elasticsearch development case
 
안정적인 서비스 운영 2014.03
안정적인 서비스 운영   2014.03안정적인 서비스 운영   2014.03
안정적인 서비스 운영 2014.03
 
Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기
Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기
Elasticsearch와 Python을 이용하여 맨땅에서 데이터 분석하기
 
Deep Dive on Amazon DynamoDB
Deep Dive on Amazon DynamoDB Deep Dive on Amazon DynamoDB
Deep Dive on Amazon DynamoDB
 
[236] 카카오의데이터파이프라인 윤도영
[236] 카카오의데이터파이프라인 윤도영[236] 카카오의데이터파이프라인 윤도영
[236] 카카오의데이터파이프라인 윤도영
 
Building a Moodle theme with bootstrap
Building a Moodle theme with bootstrapBuilding a Moodle theme with bootstrap
Building a Moodle theme with bootstrap
 
Build RESTful API Using Express JS
Build RESTful API Using Express JSBuild RESTful API Using Express JS
Build RESTful API Using Express JS
 
Advanced angular
Advanced angularAdvanced angular
Advanced angular
 
AWSKRUG-33번째-세션1.pdf
AWSKRUG-33번째-세션1.pdfAWSKRUG-33번째-세션1.pdf
AWSKRUG-33번째-세션1.pdf
 

Similar to 텍스트 랭크 알고리즘을 이용한 실시간 이슈 데이터 분석법

Towards formal verification of neural networks
Towards formal verification of neural networksTowards formal verification of neural networks
Towards formal verification of neural networks
Masahiro Sakai
 
Good Lynx, bad Lynx: Document enrichment for historical ecologists
Good Lynx, bad Lynx: Document enrichment for historical ecologistsGood Lynx, bad Lynx: Document enrichment for historical ecologists
Good Lynx, bad Lynx: Document enrichment for historical ecologists
Marieke van Erp
 
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
Koichiro tamura
 
Patakis themata tth
Patakis themata tthPatakis themata tth
MBA marks card
MBA marks cardMBA marks card
MBA marks card
Tahir Ahmad Khan
 
EJES Y ARBOLES
EJES Y ARBOLESEJES Y ARBOLES
EJES Y ARBOLES
josegonzalezsalazar
 
Prelude to halide_public
Prelude to halide_publicPrelude to halide_public
Prelude to halide_public
Fixstars Corporation
 
音響信号に対する異常音検知技術と応用
音響信号に対する異常音検知技術と応用音響信号に対する異常音検知技術と応用
音響信号に対する異常音検知技術と応用
Yuma Koizumi
 
191010 opie2
191010 opie2191010 opie2
191010 opie2
OSSラボ株式会社
 
Google translate neural machine translation post-editing evaluation
Google translate neural machine translation post-editing evaluationGoogle translate neural machine translation post-editing evaluation
Google translate neural machine translation post-editing evaluation
Masaru Yamada
 
Py con 2018_youngsooksong
Py con 2018_youngsooksongPy con 2018_youngsooksong
Py con 2018_youngsooksong
Young Sook Song
 
mHealth Israel_Japan MedTech & Digital Health: Go-To-Market Overview
mHealth Israel_Japan MedTech & Digital Health: Go-To-Market OverviewmHealth Israel_Japan MedTech & Digital Health: Go-To-Market Overview
mHealth Israel_Japan MedTech & Digital Health: Go-To-Market Overview
Levi Shapiro
 
TensorFlow 2: New Era of Developing Deep Learning Models
TensorFlow 2: New Era of Developing Deep Learning ModelsTensorFlow 2: New Era of Developing Deep Learning Models
TensorFlow 2: New Era of Developing Deep Learning Models
Jeongkyu Shin
 
AWSでの機械学習におけるデータレイク・GPU実行環境
AWSでの機械学習におけるデータレイク・GPU実行環境AWSでの機械学習におけるデータレイク・GPU実行環境
AWSでの機械学習におけるデータレイク・GPU実行環境
Yasuhiro Matsuo
 
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
Yuma Koizumi
 
[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크
[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크
[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크
OpenStack Korea Community
 
PostgreSQL Day italy 2016 Unit Test
PostgreSQL Day italy 2016 Unit TestPostgreSQL Day italy 2016 Unit Test
PostgreSQL Day italy 2016 Unit Test
Andrea Adami
 
H2O World - PAAS: Predictive Analytics offered as a Service - Prateem Mandal
H2O World - PAAS: Predictive Analytics offered as a Service - Prateem MandalH2O World - PAAS: Predictive Analytics offered as a Service - Prateem Mandal
H2O World - PAAS: Predictive Analytics offered as a Service - Prateem Mandal
Sri Ambati
 
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
Takeshi Mikami
 
Kubernetes ネットワーキングのすべて
Kubernetes ネットワーキングのすべてKubernetes ネットワーキングのすべて
Kubernetes ネットワーキングのすべて
LINE Corporation
 

Similar to 텍스트 랭크 알고리즘을 이용한 실시간 이슈 데이터 분석법 (20)

Towards formal verification of neural networks
Towards formal verification of neural networksTowards formal verification of neural networks
Towards formal verification of neural networks
 
Good Lynx, bad Lynx: Document enrichment for historical ecologists
Good Lynx, bad Lynx: Document enrichment for historical ecologistsGood Lynx, bad Lynx: Document enrichment for historical ecologists
Good Lynx, bad Lynx: Document enrichment for historical ecologists
 
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
 
Patakis themata tth
Patakis themata tthPatakis themata tth
Patakis themata tth
 
MBA marks card
MBA marks cardMBA marks card
MBA marks card
 
EJES Y ARBOLES
EJES Y ARBOLESEJES Y ARBOLES
EJES Y ARBOLES
 
Prelude to halide_public
Prelude to halide_publicPrelude to halide_public
Prelude to halide_public
 
音響信号に対する異常音検知技術と応用
音響信号に対する異常音検知技術と応用音響信号に対する異常音検知技術と応用
音響信号に対する異常音検知技術と応用
 
191010 opie2
191010 opie2191010 opie2
191010 opie2
 
Google translate neural machine translation post-editing evaluation
Google translate neural machine translation post-editing evaluationGoogle translate neural machine translation post-editing evaluation
Google translate neural machine translation post-editing evaluation
 
Py con 2018_youngsooksong
Py con 2018_youngsooksongPy con 2018_youngsooksong
Py con 2018_youngsooksong
 
mHealth Israel_Japan MedTech & Digital Health: Go-To-Market Overview
mHealth Israel_Japan MedTech & Digital Health: Go-To-Market OverviewmHealth Israel_Japan MedTech & Digital Health: Go-To-Market Overview
mHealth Israel_Japan MedTech & Digital Health: Go-To-Market Overview
 
TensorFlow 2: New Era of Developing Deep Learning Models
TensorFlow 2: New Era of Developing Deep Learning ModelsTensorFlow 2: New Era of Developing Deep Learning Models
TensorFlow 2: New Era of Developing Deep Learning Models
 
AWSでの機械学習におけるデータレイク・GPU実行環境
AWSでの機械学習におけるデータレイク・GPU実行環境AWSでの機械学習におけるデータレイク・GPU実行環境
AWSでの機械学習におけるデータレイク・GPU実行環境
 
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
 
[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크
[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크
[OpenInfra Days Korea 2018] (Track 4) - Backend.AI: 오픈소스 머신러닝 인프라 프레임워크
 
PostgreSQL Day italy 2016 Unit Test
PostgreSQL Day italy 2016 Unit TestPostgreSQL Day italy 2016 Unit Test
PostgreSQL Day italy 2016 Unit Test
 
H2O World - PAAS: Predictive Analytics offered as a Service - Prateem Mandal
H2O World - PAAS: Predictive Analytics offered as a Service - Prateem MandalH2O World - PAAS: Predictive Analytics offered as a Service - Prateem Mandal
H2O World - PAAS: Predictive Analytics offered as a Service - Prateem Mandal
 
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
 
Kubernetes ネットワーキングのすべて
Kubernetes ネットワーキングのすべてKubernetes ネットワーキングのすべて
Kubernetes ネットワーキングのすべて
 

Recently uploaded

[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...
[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...
[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...
Jason Yip
 
Fueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte WebinarFueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte Webinar
Zilliz
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
Neo4j
 
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
Northern Engraving | Modern Metal Trim, Nameplates and Appliance PanelsNorthern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
Northern Engraving
 
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham HillinQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
LizaNolte
 
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
"$10 thousand per minute of downtime: architecture, queues, streaming and fin..."$10 thousand per minute of downtime: architecture, queues, streaming and fin...
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
Fwdays
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
Javier Junquera
 
Essentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation ParametersEssentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation Parameters
Safe Software
 
"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota
Fwdays
 
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptxThe Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
operationspcvita
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
DianaGray10
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
Antonios Katsarakis
 
Astute Business Solutions | Oracle Cloud Partner |
Astute Business Solutions | Oracle Cloud Partner |Astute Business Solutions | Oracle Cloud Partner |
Astute Business Solutions | Oracle Cloud Partner |
AstuteBusiness
 
Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
c5vrf27qcz
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...
Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...
Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...
Pitangent Analytics & Technology Solutions Pvt. Ltd
 
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
Edge AI and Vision Alliance
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
akankshawande
 
A Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's ArchitectureA Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's Architecture
ScyllaDB
 

Recently uploaded (20)

[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...
[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...
[OReilly Superstream] Occupy the Space: A grassroots guide to engineering (an...
 
Fueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte WebinarFueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte Webinar
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
 
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
Northern Engraving | Modern Metal Trim, Nameplates and Appliance PanelsNorthern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
 
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham HillinQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
 
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
"$10 thousand per minute of downtime: architecture, queues, streaming and fin..."$10 thousand per minute of downtime: architecture, queues, streaming and fin...
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
 
Essentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation ParametersEssentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation Parameters
 
"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota"Choosing proper type of scaling", Olena Syrota
"Choosing proper type of scaling", Olena Syrota
 
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptxThe Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
 
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity serverDandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
 
Astute Business Solutions | Oracle Cloud Partner |
Astute Business Solutions | Oracle Cloud Partner |Astute Business Solutions | Oracle Cloud Partner |
Astute Business Solutions | Oracle Cloud Partner |
 
Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...
Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...
Crafting Excellence: A Comprehensive Guide to iOS Mobile App Development Serv...
 
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
“Temporal Event Neural Networks: A More Efficient Alternative to the Transfor...
 
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development ProvidersYour One-Stop Shop for Python Success: Top 10 US Python Development Providers
Your One-Stop Shop for Python Success: Top 10 US Python Development Providers
 
A Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's ArchitectureA Deep Dive into ScyllaDB's Architecture
A Deep Dive into ScyllaDB's Architecture
 

텍스트 랭크 알고리즘을 이용한 실시간 이슈 데이터 분석법

  • 1. Real-time Issue Data Analysis Using TextRank Algorithm
  • 2. I N T R O D U C E M Y S E L F JADE YEOM; Software Engineer & UX/UI Designer 1999.11.21 “EXPERIMENT, FAIL, LEARN, REPEAT.” Education February, 2018 - 14 1 February, 2015 - Careers April, 2016 - Founder March, 2016 ~ April, 2017 - Software Engineer Awards 30 Oct, 2013 - (SchoolSOS) 31 October, 2014 - (QuickTask) SKPlanet Smarteen App Challenge 2015 August, 2015 - ( do:learn) 2016 UNIST August, 2016 - 8 July, 2017 - ( ) E X P E R I M E N T, F A I L , L E A R N , R E P E AT.
  • 3. 1
  • 4. P R O B L E M S A N D R E S E A R C H M E T H O D S
  • 5. P R O B L E M S A N D R E S E A R C H M E T H O D S
  • 6. 1 500   . P R O B L E M S A N D R E S E A R C H M E T H O D S
  • 7. ? P R O B L E M S A N D R E S E A R C H M E T H O D S ?
  • 8. * 2014 P R O B L E M S A N D R E S E A R C H M E T H O D S
  • 9. , . ? P R O B L E M S A N D R E S E A R C H M E T H O D S !
  • 10. P R O B L E M S A N D R E S E A R C H M E T H O D S 1 2 3
  • 11. 2
  • 12. PA G E R A N K A L G O R I T H M (Vertex) , (Edge) (In graph theory)
  • 13. A 0.25 B 0.25 C 0.25 D 0.25 PA G E R A N K A L G O R I T H M A-D / B-C,D / C-B,D / D-A,B,C . A D 0.25 B C, D 0.125 C B, D 0.125 D A, B, C 0.08333 ( )
  • 14. PA G E R A N K A L G O R I T H M A 0.083 B 0.208 C D 0.50.208 A-D / B-C,D / C-B,D / D-A,B,C . A D 0.25 B C, D 0.125 C B, D 0.125 D A, B, C 0.08333 ( )
  • 15. T E X T R A N K A L G O R I T H M A 0.083 B 0.208 C D 0.50.208 , . , . TextRank: Bringing Order into Texts Rada Mihalcea and Paul Tarau
  • 16. 3
  • 17. T E X T R A N K A L G O R I T H M (Schema)
  • 18. T E X T R A N K A L G O R I T H M 30
  • 19. 4
  • 20. T E X T R A N K A L G O R I T H M 7 1,000 7 KSCY 20 21 . , , 1,000 . ( , ) ( , 2 ) / , , . 20 . KSCY , , , , - , Global Session 9 30 . . , , 1 11 (www.kscy.kr) . KSCY , , . 9 (Sentence) 211 (Noun) .
  • 21. T E X T R A N K A L G O R I T H M , , 1 11 (www.kscy.kr) . B , , 1,000 . A SENTENCE SENTENCE , , , , , , , , , , , , , , , , , , , , , , A NOUNS , , , , , , , , , , , , , , , , , , , , , , B NOUNS
  • 22. ? ! T E X T R A N K A L G O R I T H M
  • 23. * (Cosine Similarity) (Structural Equivalence) T E X T R A N K A L G O R I T H M
  • 24. T E X T R A N K A L G O R I T H M
  • 25. T E X T R A N K A L G O R I T H M , , 1,000 . A SENTENCE , , 1 11 (www.KSCY.kr) . B SENTENCE 0.60000 .
  • 26. TR 3 , , 1,000 0.16804301901203098 4 ( , ) ( , 2 ) / , , 0.12720921437593927 2 7 KSCY 20 21 . 0.12403895720955871 8 , , 1 11 (www.KSCY.kr) . 0.12161567732116019 9 KSCY , , 0.11094304196222915 5 KSCY , , , , - , Global Session 9 30 0.09781542856211028 5 20 0.09671097626842523 7 0.08109264598251792 1 7 1,000 0.07253103930602833 T E X T R A N K A L G O R I T H M
  • 27. 7 1,000 7 KSCY 20 21 . , , 1,000 . ( , ) ( , 2 ) / , , . 20 . KSCY , , , , - , Global Session 9 30 . . , , 1 11 (www.KSCY.kr) . KSCY , , . 30% 7 KSCY 20 21 . , , 1,000 . ( , ) ( , 2 ) / , , . 30% T E X T R A N K A L G O R I T H M
  • 28. T E X T R A N K A L G O R I T H M , . ' ' . 10 SNS  " # # " . . . (11 ) ' ' 1 6 vs MVP,  8  vs  .
  • 29. T E X T R A N K A L G O R I T H M TR 2 10 SNS " # # " , , , , , , , , , , 0.3644289912306943 1 ' ' . , , , , , , , , , 0.17644170069290174 3 . , , , , , , , 0.17348340763075204 5 (11 ) ' ' 1 6 vs MVP,  8  vs  , , , , , , , , , , , 0.1446443616177518 4 , , , , , , 0.14100153882790015
  • 30. / (Jaccard Transformed Index For Specific Union) T E X T R A N K A L G O R I T H M ' ' . A SENTENCE (11 ) ' ' 1 6 vs MVP,  8  vs  B SENTENCE 0.04347826 0.13043478
  • 31. T E X T R A N K A L G O R I T H M TR 5 (11 ) ' ' 1 6 vs MVP,  8  vs  , , , , , , , , , , , , , 0.36405889831533783 1 ' ' . , , , , , , , , , 0.20943504244072794 4 , , , , , , , 0.14793614614904468 3 , , , , , , , , , , , 0.14014931482237628 2 10 SNS  " # # " . , , , , , , 0.13842059827251335
  • 32. “ 5 . HQ .” “ 1 .” “ 5 .” 1. “ 5 , 1 .” 2. T E X T R A N K A L G O R I T H M
  • 33. “ 5 , 1 . .” 3. . T E X T R A N K A L G O R I T H M
  • 34. 4. , . keyword summary_issue started_at ended_at rank_avg . . 2017-07-10 16:19:14 2017-07-10 20:32:30 3.8 . . ' ' . 2017-07-10 14:18:41 2017-07-10 16:19:00 2.4 2015 . . 2017-07-10 08:18:41 2017-07-10 10:12:30 5.3 T E X T R A N K A L G O R I T H M
  • 35. 5
  • 36. R E S U LT S
  • 37. F U T U R E R E S E A R C H A N D E X P E C T E D E F F E C T S .
  • 38. https://rankr.kr https://github.com/endlessdev/summarizer F U T U R E R E S E A R C H A N D E X P E C T E D E F F E C T S
  • 39. Real-time Issue Data Analysis Using TextRank Algorithm
  • 40. Real-time Issue Data Analysis Using TextRank Algorithm THANK YOU FOR ATTENTION.