improving twitter retrieval by exploiting structural
play

Improving Twitter Retrieval by Exploiting Structural Information - PowerPoint PPT Presentation

Sep 24, 2023 •580 likes •1.27k views

Improving Twitter Retrieval by Exploiting Structural Information Zhunchen Luo, Miles Osborne, Sasa Petrovic and Ting Wang Twitter Retrieval Most Twitter search systems treat a tweet as a plain text. A tweet

  1. Improving Twitter Retrieval by Exploiting Structural Information Zhunchen ¡Luo, ¡ Miles ¡Osborne, ¡ Sasa ¡Petrovic ¡and ¡Ting ¡Wang

  2. Twitter Retrieval • Most Twitter search systems treat a tweet as a plain text. • A tweet can be seen as structured text. • Goal: Improve Twitter retrieval by exploiting structural information.

  3. Structured Tweets

  4. Structured Tweets Plan Text:

  5. Structured Tweets Plan Text:

  6. Structured Tweets Plan Text: Text+Link:

  7. Structured Tweets Plan Text: Text+Link:

  8. Structured Tweets Plan Text: Text+Link: Complex Structures (include hashtag, mention, etc):

  9. Structured Tweets Plan Text: Text+Link: Complex Structures (include hashtag, mention, etc):

  10. Our Work

  11. Our Work • We propose Twitter Building Blocks (TBBs ) to capture the structural information of tweets.

  12. Our Work • We propose Twitter Building Blocks (TBBs ) to capture the structural information of tweets. • Learning-to-rank for Twitter retrieval • Structural information features ( TBB features ). • Social media features (e.g, author social network information).

  13. Twitter Building Blocks (TBBs)

  14. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens.

  15. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs:

  16. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs: • TAG: hashtag, e.g., #keywords.

  17. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs: • TAG: hashtag, e.g., #keywords. • MET: mention symbols e.g., @username.

  18. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs: • TAG: hashtag, e.g., #keywords. • MET: mention symbols e.g., @username. • RWT: retweet symbols, e.g., RT @username, RT, via @username.

  19. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs: • TAG: hashtag, e.g., #keywords. • MET: mention symbols e.g., @username. • RWT: retweet symbols, e.g., RT @username, RT, via @username. • URL: links.

  20. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs: • TAG: hashtag, e.g., #keywords. • MET: mention symbols e.g., @username. • RWT: retweet symbols, e.g., RT @username, RT, via @username. • URL: links. • COM: comment.

  21. Twitter Building Blocks (TBBs) • TBB is a sequence of tokens. • Six types of TBBs: • TAG: hashtag, e.g., #keywords. • MET: mention symbols e.g., @username. • RWT: retweet symbols, e.g., RT @username, RT, via @username. • URL: links. • COM: comment. • MSG: content.

  22. TBB Structures • TBB structure is a combination of TBBs

  23. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :(

  24. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :(

  25. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :(

  26. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( COM

  27. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( COM

  28. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( COM

  29. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT COM

  30. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT COM

  31. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT COM

  32. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT MET COM

  33. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT MET COM

  34. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT MET COM

  35. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT MET MSG COM

  36. TBB Structures • TBB structure is a combination of TBBs U need an iphone lol ==> RT @UserB: @UserA i nearly dropped my blackberry in that poool :( RWT MET MSG COM • TBB Structure is “ COM RWT MET MSG ”.

  37. TBB Structures • TBB structure is a combinations of TBB

  38. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple

  39. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple

  40. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple

  41. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple MSG

  42. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple MSG

  43. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple MSG

  44. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple MSG URL

  45. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple MSG URL

  46. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple MSG URL

  47. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple TAG MSG URL

  48. TBB Structures • TBB structure is a combinations of TBB New IPhone in Semptember ---- http: //buswk.co/jbyCo #iphone #apple TAG MSG URL • TBB Structure is “ MSG URL TAG ”.

  49. TBB Structures Distribution

  50. TBB Structures Distribution • 14 most frequent TBB Structures in Twitter. • “OTHERS” accounts for all other TBB Structures.

  51. TBB Structures Distribution • 14 most frequent TBB Structures in Twitter. • “OTHERS” accounts for all other TBB Structures. TBB Structures (%) TBB Structures (%) MSG 30.25 TAG MSG 1.55 MET MSG TAG MSG URL 20.70 1.20 MSG URL RWT MSG URL 18.40 0.95 OTHERS 13.20 COM RWT MSG 0.85 COM URL 4.10 MET MSG URL 0.85 MSG TAG MSG MET MSG 2.65 0.70 MSG URL TAG RWT MSG TAG 2.10 0.70 RWT MSG 1.75

  52. TBB Structures Distribution • 14 most frequent TBB Structures in Twitter. • “OTHERS” accounts for all other TBB Structures. TBB Structures (%) TBB Structures (%) MSG 30.25 TAG MSG 1.55 MET MSG TAG MSG URL 20.70 1.20 MSG URL RWT MSG URL 18.40 0.95 OTHERS 13.20 COM RWT MSG 0.85 COM URL 4.10 MET MSG URL 0.85 MSG TAG MSG MET MSG 2.65 0.70 MSG URL TAG RWT MSG TAG 2.10 0.70 RWT MSG 1.75 • People use simple and fixed structures to tweet.

  53. Automatic TBB Tagger • Sequence labeling approach (Conditional Random Field). • Features for TBB tagger: • Token type; Pos; Length; Prefix and suffix; Twitter orthography (e.g, the preceding of “RWT” is more likely to be “COM” ). • TBB structure identification achieves an accuracy of 82.60%. • #(Train dataset)=1000; #(Dev dataset)=500; #(Test dataset)=500;

  54. TBB Analysis

  55. TBB Analysis • Clustering tweets by TBB structures.

  56. TBB Analysis • Clustering tweets by TBB structures. • Each cluster has similar characteristics:

  57. TBB Analysis • Clustering tweets by TBB structures. • Each cluster has similar characteristics: • Public Broadcast: MSG URL; MSG URL TAG • E.g., Apple brings new iPad to China http://bbc.in/Nl2HW9

  58. TBB Analysis • Clustering tweets by TBB structures. • Each cluster has similar characteristics: • Public Broadcast: MSG URL; MSG URL TAG • E.g., Apple brings new iPad to China http://bbc.in/Nl2HW9 • Subjective Text: COM RWT MSG,(Opinion Retrieval in Twitter. Luo et al, ICWSM-12) • E.g, I thought we were isolated and no one would want to invest here! RT @UserA: Honda announces 500 new jobs in Swindon

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Propagated Opinion Retrieval in Twitter Zhunchen Luo, Jintao Tang and Ting

Propagated Opinion Retrieval in Twitter Zhunchen Luo, Jintao Tang and Ting

Propagated Opinion Retrieval in Twitter Zhunchen Luo, Jintao Tang and Ting Wang Opinion Retrieval in Twitter Extension work: opinion retrieval in Twitter ( ICWSM 2012 ) Twitter: an important source for people to

405 views • 24 slides
Models for Models for Retrieval and Browsing Retrieval and Browsing - Structural Models and

Models for Models for Retrieval and Browsing Retrieval and Browsing - Structural Models and

Models for Models for Retrieval and Browsing Retrieval and Browsing - Structural Models and Browsing Berlin Chen 2004 Reference : 1. Modern Information Retrieval , chapter 2 Taxonomy of Classic IR Models Set Theoretic Fuzzy Extended Boolean

837 views • 29 slides
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models

Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models

Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models Jiuxiang Gu Jianfei Cai Shafiq Joty Li Niu Gang Wang Goal Text-to-Image Retrieval Image-to-Text Retrieval A young man doing a

520 views • 15 slides
Good progress towards 2020 ambition Exploiting opportunities in an improving market

Good progress towards 2020 ambition Exploiting opportunities in an improving market

Analysts and Investors Call 2020 Good progress towards 2020 ambition Exploiting opportunities in an improving market environment 28 February 2020 Please note: Presentation based on 2019 preliminary figures Image: Klaus Ohlenschlger /

1.74k views • 111 slides
XML Retrieval XML Retrieval XML Retrieval XML Retrieval DB/IR in DB/IR in Theory Theory Web

XML Retrieval XML Retrieval XML Retrieval XML Retrieval DB/IR in DB/IR in Theory Theory Web

XML Retrieval XML Retrieval XML Retrieval XML Retrieval DB/IR in DB/IR in Theory Theory Web in Web in Practice Practice Sihem Amer-Yahia Mariano Consens Yahoo! Research University of Toronto In collaboration with: Ricardo Baeza-Yates

1.06k views • 59 slides
Good progress towards 2020 ambition Exploiting opportunities in an improving market

Good progress towards 2020 ambition Exploiting opportunities in an improving market

Balance sheet media conference for 2019 financial statements Good progress towards 2020 ambition Exploiting opportunities in an improving market environment 28 February 2020 Please note: Presentation based on 2019 preliminary figures Image:

665 views • 37 slides
(Pseudo)-Relevance Feedback & Passage Retrieval Ling573 NLP Systems & Applications

(Pseudo)-Relevance Feedback & Passage Retrieval Ling573 NLP Systems & Applications

(Pseudo)-Relevance Feedback & Passage Retrieval Ling573 NLP Systems & Applications April 28, 2011 Roadmap Retrieval systems Improving document retrieval Compression & Expansion techniques Passage retrieval:

926 views • 78 slides
Improving microwave precipitation retrieval using total lightning data: A look into GOES-R and

Improving microwave precipitation retrieval using total lightning data: A look into GOES-R and

Improving microwave precipitation retrieval using total lightning data: A look into GOES-R and GPM multi-sensor and multi- platform era Rachel Albrecht 1,2 , Kaushik Gopalan 2 , Nai-Yu Wang 2 , Eric Bruning 3,2 , Steve Goodman 4,5 , Ralph Ferraro

547 views • 12 slides
Improving precipitation retrieval using total Improving precipitation retrieval using total

Improving precipitation retrieval using total Improving precipitation retrieval using total

Improving precipitation retrieval using total Improving precipitation retrieval using total lightning data: a multi lightning data: a multi-sensor, multi sensor, multi-platform platform synergy between GOES synergy between GOES-R and GPM R

483 views • 12 slides
Considerations for Improving Performance at Geotechnical-Structural Interfaces J. David Frost,

Considerations for Improving Performance at Geotechnical-Structural Interfaces J. David Frost,

Considerations for Improving Performance at Geotechnical-Structural Interfaces J. David Frost, Ph.D., P.E., P.Eng., F.ASCE Professor of Civil & Environmental Engineering Georgia Institute of Technology J-Rapid Symposium Sendai, Japan

664 views • 20 slides
Improving Shape retrieval by Spectral Matching and Meta Similarity Amir Egozi (BGU), Yosi Keller

Improving Shape retrieval by Spectral Matching and Meta Similarity Amir Egozi (BGU), Yosi Keller

Improving Shape retrieval by Spectral Matching and Meta Similarity Amir Egozi (BGU), Yosi Keller (BIU) and Hugo Guterman (BGU) Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev 1 / 21 Talk Outline Problem

999 views • 48 slides
Improving forecasting by estimating time series structural components across multiple frequencies

Improving forecasting by estimating time series structural components across multiple frequencies

Improving forecasting by estimating time series structural components across multiple frequencies Nikolaos Kourentzes Fotios Petropoulos Juan R. Trapero Multiple Aggregation Prediction Algorithm Agenda 1. Motivation 2. The idea behind the

573 views • 21 slides
Information Retrieval Introducing Information Retrieval and Web Search Information Retrieval

Information Retrieval Introducing Information Retrieval and Web Search Information Retrieval

Introduction to Information Retrieval Introducing Information Retrieval and Web Search Information Retrieval Information Retrieval (IR) is finding material (usually documents) of an unstructured nature (usually text) that satisfies an

1.01k views • 57 slides
Improving genome assemblies, assessing structural variation and trait association using chromosome

Improving genome assemblies, assessing structural variation and trait association using chromosome

Improving genome assemblies, assessing structural variation and trait association using chromosome genomics and Illumina skim genotyping by sequencing David Edwards University of Queensland, Australia Dave.Edwards@uq.edu.au 1 Outline

589 views • 30 slides
Improving Running Components Evan Weaver Twitter, Inc. QCon London, 2009 Many tools: Rails C

Improving Running Components Evan Weaver Twitter, Inc. QCon London, 2009 Many tools: Rails C

Improving Running Components Evan Weaver Twitter, Inc. QCon London, 2009 Many tools: Rails C Scala Java MySQL Rails front-end: rendering cache composition db querying Middleware: Memcached Varnish (cache) Kestrel (MQ) comet server

799 views • 43 slides
Using Twitter for your CPD Janet Thomas November 2019 #PHYSIO19 Why twitter for CPD?

Using Twitter for your CPD Janet Thomas November 2019 #PHYSIO19 Why twitter for CPD?

Using Twitter for your CPD Janet Thomas November 2019 #PHYSIO19 Why twitter for CPD? Twitter is free! Twitter is flexible CPD from your phone Twitter crosses professional, hierarchical and geographical boundaries You

595 views • 13 slides
SBND Detector Ting Miao (FNAL) Neutrino - Latin America Workshop April 27, 2016 SBND - S hort- B

SBND Detector Ting Miao (FNAL) Neutrino - Latin America Workshop April 27, 2016 SBND - S hort- B

SBND Detector Ting Miao (FNAL) Neutrino - Latin America Workshop April 27, 2016 SBND - S hort- B aseline N ear D etector A near detector project in the three-detector SBN program Ting Miao Technical Coordinator/Manager A FNAL

912 views • 14 slides
Automatic Outlier Detection: A Bayesian Approach Jo-Anne Ting, University of Southern California

Automatic Outlier Detection: A Bayesian Approach Jo-Anne Ting, University of Southern California

Automatic Outlier Detection: A Bayesian Approach Jo-Anne Ting, University of Southern California Aaron DSouza, Google, Inc. Stefan Schaal, University of Southern California ICRA 2007 April 12, 2007 Outline Motivation Past &

861 views • 21 slides
Budget Kickoff February 27, 2018 1 Governor's Finance Office BUDGET KICKOFF 2019 2021

Budget Kickoff February 27, 2018 1 Governor's Finance Office BUDGET KICKOFF 2019 2021

BUDGET KICKOFF 2019 2021 Executive Budget Budget Kickoff February 27, 2018 1 Governor's Finance Office BUDGET KICKOFF 2019 2021 Executive Budget Questions during the meeting Budget@finance.nv.gov Raise your hand 3x5

1.89k views • 140 slides
Multilevel optimization by space-filling curves in adaptive atmospheric modeling Jrn Behrens

Multilevel optimization by space-filling curves in adaptive atmospheric modeling Jrn Behrens

Multilevel optimization by space-filling curves in adaptive atmospheric modeling Jrn Behrens Technische Universitt Mnchen Center for Math. Sciences (M3) 85747 Garching, Germany behrens@ma.tum.de www-m3.ma.tum.de/m3/behrens

542 views • 25 slides
Finding and Understanding Bugs in Software Model Checkers Chengyu Zhang , Ting Su, Yichen Yan,

Finding and Understanding Bugs in Software Model Checkers Chengyu Zhang , Ting Su, Yichen Yan,

Finding and Understanding Bugs in Software Model Checkers Chengyu Zhang , Ting Su, Yichen Yan, Fuyuan Zhang, Geguang Pu, Zhendong Su Software Model Checking 2 Software Model Checking P 3 Software Model Checking P 4 Software

1.41k views • 114 slides
MatrixKV: Reducing Write Stalls and Write Amplification in LSM-tree Based KV Stores with a Matrix

MatrixKV: Reducing Write Stalls and Write Amplification in LSM-tree Based KV Stores with a Matrix

MatrixKV: Reducing Write Stalls and Write Amplification in LSM-tree Based KV Stores with a Matrix Container in NVM Ting Yao 1 , Yiwen Zhang 1 , Jiguang Wan 1 , Qiu Cui 2 , Liu Tang 2 , Hong Jiang 3 , Changsheng Xie 1 , and Xubin He 4 1 Huazhong

545 views • 27 slides
Using Derivatives in an Economics Set- ting. LectroCopy makes photocopy machines, and

Using Derivatives in an Economics Set- ting. LectroCopy makes photocopy machines, and

MarginsEcon.nb 1 Using Derivatives in an Economics Set- ting. LectroCopy makes photocopy machines, and sells them to make money. If they make x copy machines per week, then their total costs for that week are given by

252 views • 10 slides
Grid/Clo d Comp ting Grid/Clo d Comp ting Grid/Cloud Computing Grid/Cloud Computing over

Grid/Clo d Comp ting Grid/Clo d Comp ting Grid/Cloud Computing Grid/Cloud Computing over

Grid/Clo d Comp ting Grid/Clo d Comp ting Grid/Cloud Computing Grid/Cloud Computing over Optical Networks over Optical Networks over Optical Networks over Optical Networks - Opportunities & Research Issues Opportunities & Research

405 views • 17 slides

More recommend