Difference between revisions of "Popescu and Pennacchiotti, CIKM 10"
m |
m |
||
| Line 16: | Line 16: | ||
Events are defined in relation to a target entity, which is an activity with a clear, finite duration in which the target entity plays a key role. | Events are defined in relation to a target entity, which is an activity with a clear, finite duration in which the target entity plays a key role. | ||
| − | The event is considered controversial if it provokes a public discussion in which audience members express opposing opinions or | + | The event is considered controversial if it provokes a public discussion in which audience members express opposing opinions or dis-beliefs. This is in contrast to events which have little reaction or are overwhelmingly positive/negative (i.e high entropy in opinions). |
The authors seek to extract such snapshots of controversial events by modeling the task as a supervised machine learning problem. Each snapshot is represented by a feature vector constructed from Twitter and other sources (such as news). | The authors seek to extract such snapshots of controversial events by modeling the task as a supervised machine learning problem. Each snapshot is represented by a feature vector constructed from Twitter and other sources (such as news). | ||
| Line 22: | Line 22: | ||
They make extensive use of lexicons such as | They make extensive use of lexicons such as | ||
| − | # Controversy lexicon derived from Wikipedia's controversial topic list | + | # Controversy lexicon derived from Wikipedia's controversial topic list [http://en.wikipedia.org/wiki/Wikipedia:List_of_controversial_issues] |
| − | # Bad words | + | # [[UsesDataset::Bad words lexicon]] [http://urbanoalvarez.es/blog/2008/04/04/bad-words-list/] |
They used features to capture an event snapshots' linguistic properties, structural information (graph), intensity of discussion about an entity and distribution of sentiment words in the event. | They used features to capture an event snapshots' linguistic properties, structural information (graph), intensity of discussion about an entity and distribution of sentiment words in the event. | ||
| Line 31: | Line 31: | ||
They manually labeled 800 tweets for events. Their data is not released, although they achieved high kappa score (inter annotator agreement) for their labeled data. | They manually labeled 800 tweets for events. Their data is not released, although they achieved high kappa score (inter annotator agreement) for their labeled data. | ||
| − | They compared their | + | They compared their different models by ranking quality and average precision. |
The blended model seemed to perform best on their dataset. | The blended model seemed to perform best on their dataset. | ||
| − | Hashtags were one of the most | + | Hashtags were one of the most discriminating features for event detection. Coupling tweets with news and external sources were also useful as they help to validate and explain social media reactions. |
== Discussion == | == Discussion == | ||
Revision as of 22:54, 30 September 2012
This Paper is relevant to our project on detecting controversial events in Twitter.
Contents
Detecting controversial events from Twitter
Citation
Ana-Maria Popescu and Marco Pennacchiotti. Detecting controversial events from Twitter. In Proceedings of the 19th ACM international conference on Information and knowledge management, CIKM ’10, pages 1873–1876, New York, NY, USA, 2010. ACM.
Online version
Detecting controversial events from Twitter
Summary
This paper addresses the task of identifying controversial events using Twitter as a starting point.
Events are defined in relation to a target entity, which is an activity with a clear, finite duration in which the target entity plays a key role. The event is considered controversial if it provokes a public discussion in which audience members express opposing opinions or dis-beliefs. This is in contrast to events which have little reaction or are overwhelmingly positive/negative (i.e high entropy in opinions).
The authors seek to extract such snapshots of controversial events by modeling the task as a supervised machine learning problem. Each snapshot is represented by a feature vector constructed from Twitter and other sources (such as news). They present several models for comparison, a direct model using regression, a 2-step pipeline model where one detects events and then measure its controversy, and a 2-step blended model where the results of the event detection step are used as an input to the controversy detection regression model.
They make extensive use of lexicons such as
- Controversy lexicon derived from Wikipedia's controversial topic list [1]
- Bad words lexicon [2]
They used features to capture an event snapshots' linguistic properties, structural information (graph), intensity of discussion about an entity and distribution of sentiment words in the event. Furthermore, they also align news articles to snapshot tweets and see how many news articles mentions the target entity significantly.
Evaluation
They manually labeled 800 tweets for events. Their data is not released, although they achieved high kappa score (inter annotator agreement) for their labeled data. They compared their different models by ranking quality and average precision. The blended model seemed to perform best on their dataset.
Hashtags were one of the most discriminating features for event detection. Coupling tweets with news and external sources were also useful as they help to validate and explain social media reactions.
Discussion
Related papers
There has been a lot of work on event detection.
- A Statistical Model for Popular Events Tracking in Social Communities. Lin et al, KDD 2011 This paper address a method to observe and track the popular events or topics that evolve over time in the communities.
- A study on retrospective and online event detection. Yang et al, SIGIR 98 This paper addresses the problems of detecting events in news stories.
- Temporal and information flow based event detection from social text streams. Zhao et al, AAAI 07 This paper addresses the problems of detecting events in news stories.
- Automatic Detection and Classification of Social Events. Agarwal and Rambow, ACL 10 This paper aims at detecting and classifying social events using Tree kernels.
- Information credibility on twitter. Castillo et al, WWW 11 The authors develop a general approach to change-point detection that generalize across wide range of application.
