| Project/Area Number |
26450370
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Agricultural environmental engineering/Agricultural information engineering
|
|---|
| Research Institution | National Agriculture and Food Research Organization |
|---|
Principal Investigator |
Takezaki Akane 国立研究開発法人農業・食品産業技術総合研究機構, 農業技術革新工学研究センター, 上級研究員 (40550520)
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2016: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2015: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 自然言語処理 / 野菜商品レビュー / 形態素解析 / インターネット通販 / 品種 / テキスト解析 / 品質保証要素 / レシピデータ / 消費者 / 共起ベクトル / TermExtract / 消費者語彙 / 研究者語彙 / テキストマイニング / 重要語 |
|---|
| Outline of Final Research Achievements |
In this study, we present the procedure of concept extraction based on natural language processing (NLP) from online vegetable-product reviews. The unique characteristics of vegetable product reviews made difficult to process accurately using general NLP. To improving performance of NLP on vegetable-product reviews, we proposed the customer dictionary and the concept extraction methods such as 1) morpheme analysis by reference to an additional custom dictionary, 2) acquisition of negative meaning, 3) synonymous substitution, 4) identification of target nouns that adjectives have a relationship with according to the analysis purpose.
|
