TY - JOUR

T1 - Those were the days

T2 - learning to rank social media posts for reminiscence

AU - Naini, Kaweh Djafari

AU - Kawase, Ricardo

AU - Kanhabua, Nattiya

AU - Niederée, Claudia

AU - Altingovde, Ismail Sengor

N1 - Funding information: Funding I.S. Altingovde is supported by Turkish Academy of Sciences Distinguished Young Scientist Award (TUBA-GEBIP 2016). This work was partially funded by the DFG Project “Managed Forgetting” (Contract Number NI-1760/1-1).

PY - 2019/4/15

Y1 - 2019/4/15

N2 - Social media posts are a great source for life summaries aggregating activities, events, interactions and thoughts of the last months or years. They can be used for personal reminiscence as well as for keeping track with developments in the lives of not-so-close friends. One of the core challenges of automatically creating such summaries is to decide which posts are memorable, i.e., should be considered for retention and which ones to forget. To address this challenge, we design and conduct user evaluation studies and construct a corpus that captures human expectations towards content retention. We analyze this corpus to identify a small set of seed features that are most likely to characterize memorable posts. Next, we compile a broader set of features that are leveraged to build general and personalized machine-learning models to rank posts for retention. By applying feature selection, we identify a compact yet effective subset of these features. The models trained with the presented feature sets outperform the baseline models exploiting an intuitive set of temporal and social features.

AB - Social media posts are a great source for life summaries aggregating activities, events, interactions and thoughts of the last months or years. They can be used for personal reminiscence as well as for keeping track with developments in the lives of not-so-close friends. One of the core challenges of automatically creating such summaries is to decide which posts are memorable, i.e., should be considered for retention and which ones to forget. To address this challenge, we design and conduct user evaluation studies and construct a corpus that captures human expectations towards content retention. We analyze this corpus to identify a small set of seed features that are most likely to characterize memorable posts. Next, we compile a broader set of features that are leveraged to build general and personalized machine-learning models to rank posts for retention. By applying feature selection, we identify a compact yet effective subset of these features. The models trained with the presented feature sets outperform the baseline models exploiting an intuitive set of temporal and social features.

KW - Content retention

KW - Facebook

KW - Feature selection

KW - Learning to rank

KW - Letor

KW - Personalization

KW - Personalized ranking

KW - Social features

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85052109569&partnerID=8YFLogxK

U2 - 10.1007/s10791-018-9339-9

DO - 10.1007/s10791-018-9339-9

M3 - Article

AN - SCOPUS:85052109569

VL - 22

SP - 159

EP - 187

JO - Information retrieval journal

JF - Information retrieval journal

SN - 1386-4564

IS - 1-2

ER -