Search Engines Considered Harmful: In Search of an Unbiased Web Ranking

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=TLxeaQIlaMs


Duration: 1:15:55
157 views
2

In this talk, we discuss the widespread use of Web search engines and its potential impact on the ecology of the Web. Recent studies show that a significant portion of Web accesses are referred by search engines. Furthermore, the Web-search market is increasingly dominated by a few key players. What are the implications of this heavy reliance of Web users on search engines in their pursuit of information? For example, given that search engines return currently ``popular'' pages at the top of search results, are we somehow penalizing newly-created pages that are not very well known yet? Are popular pages getting even more popular while new pages are being completely ignored? We first show that this unfortunate trend indeed exists on the Web through an experimental study based on real Web data. We then analytically estimate how much longer it takes for a new page to attract a large number of Web users when search engines return only popular pages at the top of search results. Finally, we develop new ways of ranking Web pages that can significantly reduce the potential bias of existing ranking metrics. Finally, we develop new ways of ranking Web pages that can significantly reduce the potential bias of existing ranking metrics. We believe that our proposed ranking metric has the potential to alleviate the rich-get-richer phenomenon and help new and high-quality pages get the attention that they deserve.



Other Videos By Microsoft Research


2016-09-05Constructing Broad-Coverage Knowledge Repositories by Collecting Knowledge from Volunteers
2016-09-05Controlling Overlap in Content-Oriented XML Retrieval
2016-09-05Inferring Class Invariants in object-oriented languages via abstract interpretation
2016-09-05Technology Design to Foster Collaboration: A Multidisciplinary Approach
2016-09-05Towards Concept-Based Text Understanding and Mining
2016-09-05Component Programming with Object-Oriented Signals
2016-09-05On the Capacity of Information Networks
2016-09-05One-forms and Tutte-like Embeddings
2016-09-05Personal Passion and Professional Excellence ΓÇô You canΓÇÖt have one without the other!
2016-09-05Social Mobile Applications, Location, Privacy and the Capital of Nevada [1/16]
2016-09-05Search Engines Considered Harmful: In Search of an Unbiased Web Ranking
2016-09-05Science Friction: Where the Known Meets the Unknown
2016-09-05Concave utility functions on finite sets
2016-09-05Exploring Mars by 4-Wheel Drive
2016-09-05Computing with Selfish Agents [1/2]
2016-09-05Opportunities and Challenges in End-to-End Verification of Software Systems
2016-09-05Tools and Techniques for Prototyping Future Interactions [1/2]
2016-09-05Mathematical Sketching: A New Approach for Creating and Exploring Dynamic Illustrations
2016-09-05A learning-based approach to summarization
2016-09-05Virtual machines: the ultimate tool for computer forensics
2016-09-05Headwinds and Tailwinds:  Where is the U.S. economy going?


Tags:
microsoft research