TY - GEN
T1 - Who is the Mr. Right for your brand?
T2 - 41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
AU - LIU, Yang
AU - Ko, Tobey H.
AU - Gu, Zhonglei
N1 - Publisher Copyright:
© 2018 ACM.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/6/27
Y1 - 2018/6/27
N2 - Following the rising prominence of online social networks, we observe an emerging trend for brands to adopt influencer marketing, embracing key opinion leaders (KOLs) to reach potential customers (PCs) online. Owing to the growing strategic importance of these brand key assets, this paper presents a novel feature extraction method named Multi-modal Asset-aware Projection (M2A2P) to learn a discriminative subspace from the high-dimensional multi-modal social media data for effective brand key asset discovery. By formulating a new asset-aware discriminative information preserving criterion, M2A2P differentiates with the existing multi-model feature extraction algorithms in two pivotal aspects: 1) We consider brand's highly imbalanced class interest steering towards the KOLs and PCs over the irrelevant users; 2) We consider a common observation that a user is not exclusive to a single class (e.g. a KOL can also be a PC). Experiments on a real-world apparel brand key asset dataset validate the effectiveness of the proposed method.
AB - Following the rising prominence of online social networks, we observe an emerging trend for brands to adopt influencer marketing, embracing key opinion leaders (KOLs) to reach potential customers (PCs) online. Owing to the growing strategic importance of these brand key assets, this paper presents a novel feature extraction method named Multi-modal Asset-aware Projection (M2A2P) to learn a discriminative subspace from the high-dimensional multi-modal social media data for effective brand key asset discovery. By formulating a new asset-aware discriminative information preserving criterion, M2A2P differentiates with the existing multi-model feature extraction algorithms in two pivotal aspects: 1) We consider brand's highly imbalanced class interest steering towards the KOLs and PCs over the irrelevant users; 2) We consider a common observation that a user is not exclusive to a single class (e.g. a KOL can also be a PC). Experiments on a real-world apparel brand key asset dataset validate the effectiveness of the proposed method.
KW - Brand key asset discovery
KW - Key opinion leader
KW - Multi-modal asset-aware projection
KW - Potential customer
UR - http://www.scopus.com/inward/record.url?scp=85051552489&partnerID=8YFLogxK
U2 - 10.1145/3209978.3210091
DO - 10.1145/3209978.3210091
M3 - Conference contribution
AN - SCOPUS:85051552489
T3 - 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
SP - 1113
EP - 1116
BT - 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018
PB - Association for Computing Machinery, Inc
Y2 - 8 July 2018 through 12 July 2018
ER -