[image 00300] 講演会のご案内（10月10日(木) 13:25-14:25@大阪府立大学 B4棟 西K-302室）

[Motoi Iwata]

Image-ML, Document-ML の皆様

大阪府立大学の岩田です。

ドイツ人工知能研究センターの Andreas Dengel 教授をお迎えして、
下記の通り講演会を開催いたします。

ご興味がおありの方は是非ご参加ください。
事前登録等は一切不要です。
お知り合いにご興味をもたれる方がおられましたら、
お声をかけていただければ幸いです。

よろしくお願いいたします。

岩田　基
大阪府立大学 大学院 工学研究科
知能情報工学分野 第3グループ　助教
〒599-8531　大阪府堺市中区学園町1-1
TEL/FAX: 072-254-9281　　内線6805

-------------------------------------------------

日時　：2013年10月10日（木）　13:25-14:25
場所　：大阪府立大学　B4棟 3階 西K-302室
講師　：Prof. Dr. Prof. h.c. Andreas Dengel
       ドイツ人工知能研究センター
http://www3.dfki.uni-kl.de/agd/dengel/content/index_eng.html
主催：　大阪府立大学　文書解析・知識科学研究所 (IDAKS)

講演タイトル：
Discovery and Forecasting of Trending Topics in Online Media 

講演概要：
Among the vast information available on the web, social media streams
capture what people currently pay attention to and how they feel about
certain topics. Awareness of such trending topics plays a crucial role
in multimedia systems such as trend aware recommendation and automatic
vocabulary selection for video concept detection systems. Correctly
utilizing trending topics requires a better understanding of their
various characteristics in different social media streams. To this end,
I present the first comprehensive study across three major online and
social media streams, Twitter, Google, and Wikipedia, covering thousands
of trending topics during an observation period of an entire year. Our
results indicate that depending on one's requirements one does not
necessarily have to turn to Twitter for information about current events
and that some media streams strongly emphasize content of specific
categories. As our second key contribution we further present a novel
approach for the challenging task of forecasting the life cycle
of trending topics in the very moment they emerge. Our fully automated
approach is based on a nearest neighbor forecasting technique exploiting
our assumption that semantically similar topics exhibit similar
behavior. We demonstrate on a large-scale dataset of Wikipedia page view
statistics that forecasts by the proposed approach are about 9-48k views
closer to the actual viewing statistics compared to baseline methods and
achieve a mean average percentage error of 45-19% for time periods of up
to 14 days.