Details
| Original language | English |
|---|---|
| Pages (from-to) | 159-187 |
| Number of pages | 29 |
| Journal | Information retrieval journal |
| Volume | 22 |
| Issue number | 1-2 |
| Early online date | 11 Aug 2018 |
| Publication status | Published - 15 Apr 2019 |
Abstract
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.
Keywords
- Content retention, Facebook, Feature selection, Learning to rank, Letor, Personalization, Personalized ranking, Social features, Social media
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Social Sciences(all)
- Library and Information Sciences
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Information retrieval journal, Vol. 22, No. 1-2, 15.04.2019, p. 159-187.
Research output: Contribution to journal › Article › Research › peer review
}
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 -