Aspect Based Clustering for Turkish News

Aspect Based Clustering for Turkish News

Seher Acer, Baak akar, Elif Demirli, adiye Kaptanolu Introduction Motivation Aspect Based Clustering Modeling Aspects Aspect Extraction Framing Cycle-Aware Clustering

User Interface & Demo Conclusion References 2/14 News are produced in multiple stages: Gathering, writing, editing, etc.

Subjective opinion of producers, owners, advertisers biased environment Effort needed for a comprehensive and balanced understanding of a news event A system that guides and encourages reader to read news from different perspectives 3/14

Current systems provide limited presentation of news Listing news arbitrarily or according to date A system that helps users reach news from different viewpoints via a single portal Capture the difference of aspects within articles reporting a common news story Use of advanced computational techniques of information retrieval

4/14 5/14 Aspect: keyword-weight pairs Keywords are extracted from Head, sub-head, lead

GATE (General Architecture for Text Engineering) Person, organization, location Event extraction (Zemberek) Frequently used action words/phrases 6/14 7/14

Set of articles on a news shows head-tail characteristics Head common aspects Tail uncommon aspects Separation of head and tail provides effective classification Two steps: Head-tail partitioning Tail-side clustering

8/14 Generate common-uncommon keyword sets HgP: head group proportion Calculate keyword commonness & uncommonness Commonness an article with many common keywords with high weight values Uncommonness - an article with many uncommon keywords with high weight values

9/14 Agglomerative hierarchical clustering Similarity measure Cosine similarity During Agglomerative Clustering Each object forms a cluster of its own as a singleton Pairs of clusters are merged iteratively until a

certain stopping criterion is met In the merging process - the similarity between two clusters is measured by the similarity of the most similar pair of sequences belonging to these two clusters (the single-link approach) 10/14 Simple & user-friendly Present news from different aspects fairly Motivate reader to read news from different aspects

11/14 Existing systems: Google news, Yahoo News Limited presentation News listed arbitrarily

Proposed system: Gathers same news with existing systems Clusters news according to aspects Simple user interface Easy to track news stories The approach is suitable for Turkish news 12/14

[1] Park, S., Kang, S., Lee, S., Chung, S., Song, J. Mitigating Media Bias: A Computational Approach. ACM, 2008, pp. 47-51. [2] Park, S., Kang, S., Chung, S., Song, J. NewsCube: Delivering Multiple Aspects of News to Mitigate Media Bias. ACM, 2009. [3] Cunningham, H., Maynard, D., Bontcheva, K., Tablan, V. GATE: A Framework and Graphical Development Environment for Robust NLP Tools and Applications. Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics. ACL'02, 2002. [4] Park, S., Lee, S., Song, J. Aspect-level News Browsing: Understanding News Events from Multiple Viewpoints. ACM,

2010, pp. 41-50. 13/14

Recently Viewed Presentations

  • Chest Tubes - Metropolitan Community College

    Chest Tubes - Metropolitan Community College

    Chest tubes are inserted to drain blood, fluid, or air and allow full expansion of the lungs. placed in the pleural space. The area where the tube will be inserted is numbed . PLACE THE CLIENT IN SEMI FOWLER'S TO...
  • 3rd Edition: Chapter 4 - Clark U

    3rd Edition: Chapter 4 - Clark U

    wired links. wireless links. LANs. layer-2 packet: frame,encapsulates datagram. data-link layer has responsibility of . transferring datagram from one node . to physically adjacent node over a link. 6-Link Layer and LANs
  • English SOL Institute Secondary Vocabulary & Nonfiction Reading

    English SOL Institute Secondary Vocabulary & Nonfiction Reading

    Reference within this presentation to any specific commercial or non-commercial product, process, or service by trade name, trademark, manufacturer or otherwise does not constitute or imply an endorsement, recommendation, or favoring by the Virginia Department of Education. Disclaimer
  • Crystal growth and aggregation CHAPTER 5 Nucleation (growth)

    Crystal growth and aggregation CHAPTER 5 Nucleation (growth)

    Crystalline defects. Point defects. Vacancy or interstitial atom. Dislocations (line defects) Deformation on slip plane. Planar defects. Exsolution at low T. Reduction in symmetry. Radiation defects. Inclusions: Zircon (U and Th) in biotite. Haloes of different colors. Destruction of crystal...
  • Evolution - Troup County School District

    Evolution - Troup County School District

    SCIENTIFIC THEORIES & THE THEORY OF EVOLUTION. According to most scientists, all life on Earth has a common ancestor. In order to produce the immense amount of difference among all living organisms, certain ones had to evolve into distinct species.
  • Using Symbols to Compare Unlike Fractions - doe.virginia.gov

    Using Symbols to Compare Unlike Fractions - doe.virginia.gov

    The perimeter of this figure will vary depending upon the printed size of this slide. ... The student will recognize and describe a variety of patterns . formed . using numbers, tables, and pictures, and . extend the . patterns,...
  • Dos-response Japan Nuclear Radiation

    Dos-response Japan Nuclear Radiation

    dos-response japan nuclear radiation Chernobyl Nuclear Disaster Introduction Occurred on 26th April 1986 at reactor No. 4 of nuclear power plant at Chernobyl. The operators switched off an important control system -> reactor reached unstable state -> A sudden power...
  • There is Power in Unity - WordPress.com

    There is Power in Unity - WordPress.com

    [email protected] Umoja Community History Oct 2006 - Umoja I Diablo Valley College March 2007 - Umoja II Chaffey College Oct 2007 Umoja III Chabot College Summer Retreat January 2008 - BOG Recognition Umoja Consortium Four Pilot Colleges Regional Symposiums -...