Topic Extraction Based on Knowledge Cluster in the Field of Micro-blog

Li, Ming; Zhang, Chunhong; Sun, Lijun; Shao, Xianlei

doi:10.1007/978-3-319-09339-0_55

Cited by 1 publication

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our case, a document corresponds to a meal name, which is a short noun phrase consisting typically of approximately a dozen characters. It has been reported [12] that topics for such incomplete short documents tend to be processed inaccurately.…”

Section: Foodlog: a Multimedia Food Recording Toolmentioning

confidence: 98%

See 1 more Smart Citation

Food Category Representatives: Extracting Categories from Meal Names in Food Recordings and Recipe Data

Amano

Aizawa

Ogawa

2015

2015 IEEE International Conference on Multimedia Big Data

View full text Add to dashboard Cite

FoodLog is a multimedia recording tool for producing food records for many individuals. In one year of operation, FoodLog has produced more than one million food records for meals eaten by users. We found nearly 70,000 unique food records among these data. In analyzing them, one of the challenges is to extract meal categories from such a large number of records. In this paper, we propose a method for compressing a meal name into a shorter representation. First, we collect similar meal names using a k-nearest neighbor search. Next, we construct a word graph to model the relationship between the meal names and items in the database. We select representative words by identifying minimal paths in the word graph. Finally, we obtain a few words that represent categorical information about the original meal name. We applied the method to data in food records for both FoodLog and the Rakuten Recipe database. Our results show that the method worked effectively for both datasets.

show abstract

Section: Foodlog: a Multimedia Food Recording Toolmentioning

confidence: 98%

“…When the categories are unknown, category detection methods that use a topic model [5], [12] or methods of grouping texts by document clustering [13], [17], [19] have been proposed.…”

Section: Foodlog: a Multimedia Food Recording Toolmentioning

confidence: 99%