A STUDY FOR CAPTURING DEEP IMPRESSION BY UNITING NATURAL LANGUAGE PROCESSING AND NETWORK CONSTRUCTION TECHNIQUES
| Project/Area Number |
21700240
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Kobe University |
|---|
Principal Investigator |
YAMAMOTO Eiko Kobe University, 工学研究科, 講師 (90450692)
|
|---|
| Project Period (FY) |
2009 – 2010
|
| Project Status |
Completed (Fiscal Year 2010)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2010: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2009: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 意味ネットワーク / ネットワーク構築 / 印象分析 / 自然言語処理 / 印象の源 |
|---|
| Research Abstract |
When designing products, designers need to create products that are congruent with the emotional feelings of users. This study assumes that there are some sorts of emotional "impressions", which a user derives from a product that is expected to affect user preference. In this study, we focus on deep impressions, which are defined as the impressions that are related to the deep feelings towards a product and lie under surface impressions. In order to capture the nature of deep impressions, we developed a method for constructing "virtual impression networks," which involve the notions of "structure" and "inexplicit impressions," using a semantic network. This paper, in particular, aims at understanding the manner in which people form impressions of preference. Our results indicated that it is possible to explain the difference between feelings of "like" and "dislike" using several indicators in the network theory of virtual impression networks. The process of forming the impressions of "like" is shown to differ from that of "dislike" at a deep impression level.
|
Report
(3 results)
Research Products
(11 results)
