Asia Trend Map: Forecasting “Cool Japan” Content Popularity on Web Data
Asia Trend Map: Forecasting “Cool Japan”
Content Popularity on Web Data
The University of Tokyo
• Anime, Manga and Game has become popular around the world.
• Japanese content industries are willing to promote their products
overseas under the brand of “Cool Japan”.
• However, localization processes (translation, promoting etc.) take
costs a lot of money and time.
Japan in London: Sushi, Manga, Cosplay and Camden – visitlondon.com
à Sellers need to estimate the product’s popularity in the
target market and allocate their resources strategically.
• Forecasting each product's popularity around Asian countries
based on web data from Twitter, Wikipedia and a search engine.
• Why Asia?
– Close to Japan geographically and culturally à direct economic eﬀect
– Growing market
• Why web data?
– Unauthorized copies are widely distributed around the country
à There’s diﬃculty in catching the trend from the sales data
Demonstration: Asia Trend Map
• This system can forecast about 4,000 Japanese content’s
popularity trends following 6 months for 13 countries in Asia.
Wikipedia Data Attributes
– Monthly Edit Count, Monthly Unique Editor Count, Average Edit
Count Per User ...
– Number of Forward Links, Number of Backward Links ...
– Number of International Links, Page Size, Number of Sections ...
Twitter and Search Engine
• Twitter: Extract number of tweets which includes the product
• Search Engine: Extract number of times the product name is
• We get each product’s local name utilizing Wikipedia database.
Pre-processing on Training Data
• Sales of Manga suddenly increases when new volume is out.
à We connect the peak with lines and make use of this as training
• Prediction precision is improved by applying attributes of
multiple web services.
• Especially, Wikipedia data took an importance role in predicting
the trends in more distant future.
• Among the Wikipedia data attributes, Page Content (Number of
international links, Page size, etc.) took the most important role
in predicting the trend.
• We built the forecasting system of Japanese cultural products
from web data
• We launched a website based on this system: Asia Trend Map
• We'd like to contribute to strategic planning process of "Cool
Japan" with this.