Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Topical Keyphrase Extraction
from Twitter
Abstract
In this paper, we propose to extract topical
keyphrases as one way to summarize Twitter.
1、A context-sensitive to...
Introduction
Keyphrases are defined as a short list of terms to
summarize the topics of a document.
Challenges:
1. Tweets a...
Method
Method

Topic discovery

Keywords ranking
and candidate
generation

Keyphrases
ranking
Topic discovery
A modified author-topic model called Twitter-LDA
introduced by Zhao etal.(2011)
Topical PageRank for Keyword
Ranking
The topic-specific PageRank scores: TPR

A topic context sensitive PageRank method: cT...
Topical PageRank for Keyword
Ranking
a common candidate keyphrase generation method
proposed by Mihalcea and Tarau(2004) a...
Probabilistic Models for Topical Keyphrase
Ranking
Relevance : A good keyphrase should be closely
related to the given top...
Probabilistic Models for Topical Keyphrase
Ranking
In general we can assume that P ( R = 0)>> P ( R = 1)
because there are...
Upcoming SlideShare
Loading in …5
×

Topical keyphrase extraction from twitter

771 views

Published on

Published in: Technology, Design
  • Be the first to comment

  • Be the first to like this

Topical keyphrase extraction from twitter

  1. 1. Topical Keyphrase Extraction from Twitter
  2. 2. Abstract In this paper, we propose to extract topical keyphrases as one way to summarize Twitter. 1、A context-sensitive topical PageRank method for keyword ranking 2、A probabilistic scoring function that considers both relevance and interestingness of keyphrases for keyphrase ranking
  3. 3. Introduction Keyphrases are defined as a short list of terms to summarize the topics of a document. Challenges: 1. Tweets are much shorter than traditional articles and not all tweets contain useful information; 2. Topics tend to be more diverse in Twitter than informal articles such as news reports. Keyword ranking; Candidate keyphrase generation; Keyphrase ranking.
  4. 4. Method
  5. 5. Method Topic discovery Keywords ranking and candidate generation Keyphrases ranking
  6. 6. Topic discovery A modified author-topic model called Twitter-LDA introduced by Zhao etal.(2011)
  7. 7. Topical PageRank for Keyword Ranking The topic-specific PageRank scores: TPR A topic context sensitive PageRank method: cTPR
  8. 8. Topical PageRank for Keyword Ranking a common candidate keyphrase generation method proposed by Mihalcea and Tarau(2004) as follows: 1. Select the top S keywords for each topic 2. look for combinations of these keywords that occur as frequent phrases in the text collection
  9. 9. Probabilistic Models for Topical Keyphrase Ranking Relevance : A good keyphrase should be closely related to the given topic and also discriminative. Interestingness : A good keyphrase should be interesting and can attract users’ attention.
  10. 10. Probabilistic Models for Topical Keyphrase Ranking In general we can assume that P ( R = 0)>> P ( R = 1) because there are much more non-relevant keyphrases than relevant ones,that is, δ>> 1 .

×