FNED A Deep Network for Fake News Early Detection on Social Media
The fast spreading of fake news stories on social media can cause inestimable social harm. Developing effective methods to detect them early is of paramount importance. A major challenge of fake news early detection is fully utilizing the limited data observed at the early stage of news propagation...
Saved in:
| Published in | ACM transactions on information systems Vol. 38; no. 3; pp. 1 - 33 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
01.06.2020
|
| Online Access | Get full text |
Cover
Loading…
| Abstract | The fast spreading of fake news stories on social media can cause inestimable social harm. Developing effective methods to detect them early is of paramount importance. A major challenge of fake news early detection is fully utilizing the limited data observed at the early stage of news propagation and then learning useful patterns from it for identifying fake news. In this article, we propose a novel deep neural network to detect fake news early. It has three novel components: (1) a status-sensitive crowd response feature extractor that extracts both text features and user features from combinations of users’ text response and their corresponding user profiles, (2) a position-aware attention mechanism that highlights important user responses at specific ranking positions, and (3) a multi-region mean-pooling mechanism to perform feature aggregation based on multiple window sizes. Experimental results on two real-world datasets demonstrate that our proposed model can detect fake news with greater than 90% accuracy within 5 minutes after it starts to spread and before it is retweeted 50 times, which is significantly faster than state-of-the-art baselines. Most importantly, our approach requires only 10% labeled fake news samples to achieve this effectiveness under PU-Learning settings. |
|---|---|
| AbstractList | The fast spreading of fake news stories on social media can cause inestimable social harm. Developing effective methods to detect them early is of paramount importance. A major challenge of fake news early detection is fully utilizing the limited data observed at the early stage of news propagation and then learning useful patterns from it for identifying fake news. In this article, we propose a novel deep neural network to detect fake news early. It has three novel components: (1) a status-sensitive crowd response feature extractor that extracts both text features and user features from combinations of users’ text response and their corresponding user profiles, (2) a position-aware attention mechanism that highlights important user responses at specific ranking positions, and (3) a multi-region mean-pooling mechanism to perform feature aggregation based on multiple window sizes. Experimental results on two real-world datasets demonstrate that our proposed model can detect fake news with greater than 90% accuracy within 5 minutes after it starts to spread and before it is retweeted 50 times, which is significantly faster than state-of-the-art baselines. Most importantly, our approach requires only 10% labeled fake news samples to achieve this effectiveness under PU-Learning settings. |
| Author | Wu, Yi-Fang Brook Liu, Yang |
| Author_xml | – sequence: 1 givenname: Yang surname: Liu fullname: Liu, Yang organization: New Jersey Institute of Technology, Newark, NJ – sequence: 2 givenname: Yi-Fang Brook surname: Wu fullname: Wu, Yi-Fang Brook organization: New Jersey Institute of Technology, Newark, NJ |
| BookMark | eNpljktLw0AUhYcSoS_xZ3Q1eu-8crOU2lqh6Mauwzwh0iYyk43_3ohd6eqcAx-Hb8mqfugjY3cI94hKP0hJRmg5YwvUmrggQ9XUQRlOSDRny1I-AKZtYMGq_evuac1ukj2XeHvNFTvtd-_bAz--Pb9sH4_cC6FHrhxEZ4PzGkRIgEFYRSl4A1JJ76gWMjbO21o0jbYWgzKpRkzSyOBqBLlim99fn4dSckztZ-4uNn-1CO2PfHuVn0j-h_TdaMdu6Mdsu_M__huab0QD |
| CitedBy_id | crossref_primary_10_1080_24751839_2020_1847379 crossref_primary_10_1109_ACCESS_2021_3062029 crossref_primary_10_1109_TMM_2023_3263552 crossref_primary_10_1007_s00607_025_01413_2 crossref_primary_10_1371_journal_pone_0292446 crossref_primary_10_32604_cmc_2023_038303 crossref_primary_10_1016_j_eswa_2022_118063 crossref_primary_10_1016_j_dss_2021_113633 crossref_primary_10_1016_j_fmre_2024_01_017 crossref_primary_10_1016_j_dss_2022_113911 crossref_primary_10_1007_s12652_023_04562_4 crossref_primary_10_1080_10447318_2022_2051887 crossref_primary_10_1142_S012918312250084X crossref_primary_10_1109_TBDATA_2024_3378098 crossref_primary_10_1109_TCSS_2024_3355300 crossref_primary_10_1007_s13278_024_01344_4 crossref_primary_10_1109_TDSC_2022_3165324 crossref_primary_10_3390_su142215287 crossref_primary_10_1007_s11063_021_10642_3 crossref_primary_10_1016_j_engappai_2024_108271 crossref_primary_10_1109_TKDE_2024_3496701 crossref_primary_10_1016_j_knosys_2023_110527 crossref_primary_10_1007_s43546_020_00027_4 crossref_primary_10_1016_j_ipm_2023_103366 crossref_primary_10_1016_j_ipm_2023_103520 crossref_primary_10_1007_s11257_024_09413_1 crossref_primary_10_1177_17456916221141344 crossref_primary_10_1145_3555562 crossref_primary_10_1016_j_knosys_2022_109659 crossref_primary_10_1109_TCSS_2022_3169132 crossref_primary_10_1007_s41870_024_01839_5 crossref_primary_10_1109_ACCESS_2022_3216892 crossref_primary_10_1186_s40537_023_00866_6 crossref_primary_10_1007_s00521_022_07057_z crossref_primary_10_1007_s41060_021_00302_z crossref_primary_10_1016_j_ipm_2021_102710 crossref_primary_10_32628_CSEIT23903126 crossref_primary_10_1007_s10994_024_06527_w crossref_primary_10_36930_40320612 crossref_primary_10_1007_s13278_020_00696_x crossref_primary_10_1109_ACCESS_2025_3530688 crossref_primary_10_1016_j_ipm_2021_102712 crossref_primary_10_3390_fi17010028 crossref_primary_10_1007_s00521_022_08065_9 crossref_primary_10_1007_s13278_024_01376_w crossref_primary_10_1016_j_csl_2022_101461 crossref_primary_10_3390_electronics12132942 crossref_primary_10_1016_j_ipm_2023_103279 crossref_primary_10_1145_3702639 crossref_primary_10_3390_app13148209 crossref_primary_10_1016_j_ipm_2024_103672 crossref_primary_10_1007_s13278_022_00994_6 crossref_primary_10_1016_j_future_2020_11_022 crossref_primary_10_1016_j_measen_2024_101148 crossref_primary_10_37394_23207_2023_20_126 crossref_primary_10_1016_j_eswa_2021_115002 crossref_primary_10_1016_j_jnca_2021_103112 crossref_primary_10_1017_nlp_2024_54 crossref_primary_10_1007_s11704_024_40674_6 crossref_primary_10_1016_j_matpr_2021_03_367 crossref_primary_10_1007_s10489_022_04283_9 crossref_primary_10_1038_s41598_024_82111_5 crossref_primary_10_1016_j_comcom_2022_01_003 crossref_primary_10_1016_j_ins_2024_120300 crossref_primary_10_1109_ACCESS_2023_3260763 crossref_primary_10_1145_3607253 crossref_primary_10_1109_TCSS_2023_3282572 crossref_primary_10_17721_2519_481X_2023_80_11 crossref_primary_10_15622_ia_22_4_4 crossref_primary_10_1007_s10207_022_00625_3 crossref_primary_10_32628_CSEIT2390425 crossref_primary_10_1109_TCSS_2022_3177359 crossref_primary_10_1109_TCSS_2023_3331446 crossref_primary_10_3390_a17100459 crossref_primary_10_1145_3677016 crossref_primary_10_1016_j_asoc_2024_111416 crossref_primary_10_1016_j_neucom_2022_07_057 crossref_primary_10_1016_j_asoc_2025_112965 crossref_primary_10_1007_s13369_024_09354_2 crossref_primary_10_1016_j_engappai_2023_106087 crossref_primary_10_7717_peerj_cs_2693 crossref_primary_10_1109_ACCESS_2024_3392297 crossref_primary_10_3390_s23041748 |
| Cites_doi | 10.1109/MIPR.2018.00092 10.1007/978-3-030-04503-6_4 10.1137/1.9781611974973.12 10.1145/3269206.3271709 10.1371/journal.pone.0168344 10.1145/2806416.2806607 10.1109/ACCESS.2019.2901756 10.1145/3041021.3053379 10.1145/1531914.1531924 10.1002/aris.1440370103 10.1109/ICDM.2013.61 10.1007/978-3-319-67217-5_8 10.1609/aaai.v33i01.33015644 10.1145/3132847.3132877 10.1007/11564096_24 10.1007/978-3-319-57454-7_32 10.18653/v1/P18-1184 10.1145/775047.775083 10.1038/nature14539 10.5555/2857070.2857153 10.1145/2030376.2030382 10.1109/ICACCI.2016.7732347 10.1145/3219819.3219903 10.1145/1963405.1963500 10.1007/978-3-642-37401-2_14 10.1145/2350190.2350203 10.1145/3123266.3123454 10.1126/science.aap9559 10.5555/2627435.2670313 10.1145/3308558.3313741 10.1007/978-3-319-13734-6_16 10.1109/ICDM.2014.91 10.1145/3295823 10.1109/JCSSE.2015.7219767 10.1145/2885494 10.1007/978-3-319-16268-3_13 10.18653/v1/W16-0802 10.1145/3137597.3137600 10.18653/v1/W17-1308 10.1109/tmm.2016.2617078 10.1016/j.cose.2016.12.004 10.5555/2857070.2857152 10.1109/SP.2012.34 10.1007/s13278-016-0373-6 10.1145/2983323.2983697 10.1109/BigData.2015.7364071 10.1145/2736277.2741637 10.18653/v1/P17-1066 10.1145/2806416.2806651 10.1109/ICDSP.2015.7251979 10.1137/1.9781611972825.14 10.1002/cpe.4281 10.1109/TCSS.2016.2612980 10.1007/s13278-016-0366-5 10.1109/WISA.2015.19 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION |
| DOI | 10.1145/3386253 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Business |
| EISSN | 1558-2868 |
| EndPage | 33 |
| ExternalDocumentID | 10_1145_3386253 |
| GroupedDBID | --Z -DZ -~X .4S .DC 23M 4.4 5GY 5VS 6J9 77K 85S 8US AAKMM AALFJ AAYFX AAYXX ABPPZ ACGFO ACGOD ACM ADBCU ADL ADMLS AEBYY AEFXT AEGXH AEJOY AENEX AENSD AETEA AFWIH AFWXC AIAGR AIKLT AKRVB ALMA_UNASSIGNED_HOLDINGS ARCSS ASPBG AVWKF BDXCO CCLIF CITATION CS3 D0L EBS EDO FEDTE GUFHI HGAVV H~9 I07 IAO ICD IOF LHSKQ MK~ ML~ MS~ P1C P2P PQQKQ RNS ROL RXW TAE TUS U5U UHB UPT WH7 X6Y XH6 XSW YR2 ZCA |
| ID | FETCH-LOGICAL-c225t-4b0ebadbc502df01d2a48fdc60343cb8723e9bca72995aa1d46f711f363db7103 |
| ISSN | 1046-8188 |
| IngestDate | Thu Apr 24 23:02:32 EDT 2025 Thu Jul 03 08:30:13 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c225t-4b0ebadbc502df01d2a48fdc60343cb8723e9bca72995aa1d46f711f363db7103 |
| PageCount | 33 |
| ParticipantIDs | crossref_primary_10_1145_3386253 crossref_citationtrail_10_1145_3386253 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-06-01 |
| PublicationDateYYYYMMDD | 2020-06-01 |
| PublicationDate_xml | – month: 06 year: 2020 text: 2020-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | ACM transactions on information systems |
| PublicationYear | 2020 |
| References | Qazvinian Vahed (e_1_2_1_47_1) 2011 Blitz Marc Jonathan (e_1_2_1_3_1) 2018; 71 e_1_2_1_60_1 e_1_2_1_20_1 e_1_2_1_41_1 e_1_2_1_66_1 e_1_2_1_68_1 e_1_2_1_24_1 e_1_2_1_45_1 e_1_2_1_62_1 Tolosi Laura (e_1_2_1_59_1) 2016 e_1_2_1_22_1 e_1_2_1_43_1 e_1_2_1_64_1 Li Xiaoli (e_1_2_1_27_1) 2003; 3 e_1_2_1_28_1 Galitsky Boris (e_1_2_1_10_1) 2015 e_1_2_1_26_1 Lee Wee Sun (e_1_2_1_25_1) 2003; 3 Liu Bing (e_1_2_1_29_1) e_1_2_1_71_1 Hsieh Cho-Jui (e_1_2_1_14_1) e_1_2_1_31_1 e_1_2_1_54_1 e_1_2_1_77_1 e_1_2_1_8_1 Liu Bing (e_1_2_1_30_1) 2002; 2 e_1_2_1_56_1 e_1_2_1_6_1 Spencer Sam (e_1_2_1_55_1) e_1_2_1_12_1 e_1_2_1_35_1 e_1_2_1_50_1 e_1_2_1_73_1 e_1_2_1_4_1 Ma Jing (e_1_2_1_38_1) 2016 e_1_2_1_33_1 e_1_2_1_52_1 e_1_2_1_75_1 e_1_2_1_2_1 e_1_2_1_16_1 e_1_2_1_39_1 e_1_2_1_37_1 e_1_2_1_58_1 Zhang Qiao (e_1_2_1_74_1) Hu Xia (e_1_2_1_15_1) 2013; 13 e_1_2_1_42_1 e_1_2_1_40_1 e_1_2_1_67_1 e_1_2_1_23_1 e_1_2_1_46_1 e_1_2_1_61_1 e_1_2_1_21_1 e_1_2_1_44_1 e_1_2_1_63_1 Liu Yang (e_1_2_1_34_1) 2018 Jin F. (e_1_2_1_18_1) e_1_2_1_48_1 e_1_2_1_69_1 Wu Ke (e_1_2_1_65_1) Rubin Victoria L. (e_1_2_1_49_1) Zeiler Matthew D. (e_1_2_1_72_1) 2012 e_1_2_1_70_1 e_1_2_1_7_1 e_1_2_1_76_1 e_1_2_1_5_1 e_1_2_1_57_1 e_1_2_1_78_1 e_1_2_1_13_1 e_1_2_1_51_1 e_1_2_1_1_1 e_1_2_1_11_1 e_1_2_1_32_1 e_1_2_1_53_1 e_1_2_1_17_1 e_1_2_1_36_1 e_1_2_1_9_1 e_1_2_1_19_1 |
| References_xml | – ident: e_1_2_1_54_1 doi: 10.1109/MIPR.2018.00092 – ident: e_1_2_1_5_1 doi: 10.1007/978-3-030-04503-6_4 – ident: e_1_2_1_66_1 doi: 10.1137/1.9781611974973.12 – ident: e_1_2_1_11_1 doi: 10.1145/3269206.3271709 – volume: 13 volume-title: Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI’13) year: 2013 ident: e_1_2_1_15_1 – ident: e_1_2_1_22_1 doi: 10.1371/journal.pone.0168344 – ident: e_1_2_1_39_1 doi: 10.1145/2806416.2806607 – ident: e_1_2_1_58_1 doi: 10.1109/ACCESS.2019.2901756 – volume: 3 volume-title: Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI’03) year: 2003 ident: e_1_2_1_27_1 – volume-title: Natural Language Processing and Chinese Computing ident: e_1_2_1_74_1 – volume-title: Proceedings of the 31st IEEE International Conference on Data Engineering. ident: e_1_2_1_65_1 – volume-title: Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI’16) year: 2016 ident: e_1_2_1_38_1 – ident: e_1_2_1_46_1 doi: 10.1145/3041021.3053379 – volume-title: Proceedings of the 3rd IEEE International Conference on Data Mining (ICDM’03) ident: e_1_2_1_29_1 – ident: e_1_2_1_43_1 doi: 10.1145/1531914.1531924 – ident: e_1_2_1_6_1 doi: 10.1002/aris.1440370103 – ident: e_1_2_1_23_1 doi: 10.1109/ICDM.2013.61 – ident: e_1_2_1_77_1 doi: 10.1007/978-3-319-67217-5_8 – ident: e_1_2_1_68_1 doi: 10.1609/aaai.v33i01.33015644 – ident: e_1_2_1_51_1 doi: 10.1145/3132847.3132877 – ident: e_1_2_1_28_1 doi: 10.1007/11564096_24 – ident: e_1_2_1_33_1 doi: 10.1007/978-3-319-57454-7_32 – ident: e_1_2_1_41_1 doi: 10.18653/v1/P18-1184 – ident: e_1_2_1_71_1 doi: 10.1145/775047.775083 – volume-title: ADADELTA: An adaptive learning rate method. arXiv:1212.5701. year: 2012 ident: e_1_2_1_72_1 – ident: e_1_2_1_24_1 doi: 10.1038/nature14539 – ident: e_1_2_1_45_1 – volume: 3 volume-title: Proceedings of the 20th International Conference on Machine Learning (ICML’03) year: 2003 ident: e_1_2_1_25_1 – volume-title: Proceedings of the 10th International AAAI Conference on Web and Social Media. year: 2016 ident: e_1_2_1_59_1 – ident: e_1_2_1_50_1 doi: 10.5555/2857070.2857153 – ident: e_1_2_1_62_1 doi: 10.1145/2030376.2030382 – ident: e_1_2_1_2_1 – volume-title: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. year: 2018 ident: e_1_2_1_34_1 – ident: e_1_2_1_17_1 doi: 10.1109/ICACCI.2016.7732347 – ident: e_1_2_1_64_1 doi: 10.1145/3219819.3219903 – ident: e_1_2_1_4_1 doi: 10.1145/1963405.1963500 – volume-title: Proceedings of the 2015 AAAI Spring Symposium Series. year: 2015 ident: e_1_2_1_10_1 – ident: e_1_2_1_57_1 doi: 10.1007/978-3-642-37401-2_14 – ident: e_1_2_1_67_1 doi: 10.1145/2350190.2350203 – ident: e_1_2_1_19_1 doi: 10.1145/3123266.3123454 – ident: e_1_2_1_61_1 doi: 10.1126/science.aap9559 – volume: 2 volume-title: Proceedings of the 19th International Conference on Machine Learning (ICML’02) year: 2002 ident: e_1_2_1_30_1 – ident: e_1_2_1_56_1 doi: 10.5555/2627435.2670313 – ident: e_1_2_1_42_1 doi: 10.1145/3308558.3313741 – ident: e_1_2_1_12_1 doi: 10.1007/978-3-319-13734-6_16 – volume-title: Proceedings of the 7th Workshop on Social Network Mining and Analysis. ACM ident: e_1_2_1_18_1 – ident: e_1_2_1_20_1 doi: 10.1109/ICDM.2014.91 – ident: e_1_2_1_37_1 doi: 10.1145/3295823 – ident: e_1_2_1_69_1 doi: 10.1109/JCSSE.2015.7219767 – ident: e_1_2_1_73_1 doi: 10.1145/2885494 – ident: e_1_2_1_36_1 doi: 10.1007/978-3-319-16268-3_13 – ident: e_1_2_1_48_1 doi: 10.18653/v1/W16-0802 – volume-title: Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1589--1599 year: 2011 ident: e_1_2_1_47_1 – ident: e_1_2_1_53_1 doi: 10.1145/3137597.3137600 – volume-title: Proceedings of the 32nd International Conference on Machine Learning (ICML’15) ident: e_1_2_1_14_1 – ident: e_1_2_1_9_1 doi: 10.18653/v1/W17-1308 – ident: e_1_2_1_21_1 doi: 10.1109/tmm.2016.2617078 – ident: e_1_2_1_31_1 doi: 10.1016/j.cose.2016.12.004 – ident: e_1_2_1_7_1 doi: 10.5555/2857070.2857152 – ident: e_1_2_1_78_1 doi: 10.1007/978-3-319-67217-5_8 – ident: e_1_2_1_1_1 doi: 10.1109/SP.2012.34 – ident: e_1_2_1_16_1 doi: 10.1007/s13278-016-0373-6 – volume-title: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’16) ident: e_1_2_1_55_1 – ident: e_1_2_1_52_1 doi: 10.1145/2983323.2983697 – volume-title: The SAGE Handbook of Social Media Research Methods ident: e_1_2_1_49_1 – ident: e_1_2_1_63_1 doi: 10.1109/BigData.2015.7364071 – ident: e_1_2_1_75_1 doi: 10.1145/2736277.2741637 – ident: e_1_2_1_40_1 doi: 10.18653/v1/P17-1066 – ident: e_1_2_1_32_1 doi: 10.1145/2806416.2806651 – ident: e_1_2_1_76_1 doi: 10.1109/ICDSP.2015.7251979 – volume: 71 start-page: 59 year: 2018 ident: e_1_2_1_3_1 article-title: Lies, line drawing, and deep fake news publication-title: Oklahoma Law Review – ident: e_1_2_1_13_1 doi: 10.1137/1.9781611972825.14 – ident: e_1_2_1_44_1 – ident: e_1_2_1_26_1 doi: 10.1002/cpe.4281 – ident: e_1_2_1_35_1 doi: 10.1109/TCSS.2016.2612980 – ident: e_1_2_1_8_1 doi: 10.1007/s13278-016-0366-5 – ident: e_1_2_1_70_1 doi: 10.1109/WISA.2015.19 – ident: e_1_2_1_60_1 |
| SSID | ssj0004660 |
| Score | 2.6000142 |
| SecondaryResourceType | review_article |
| Snippet | The fast spreading of fake news stories on social media can cause inestimable social harm. Developing effective methods to detect them early is of paramount... |
| SourceID | crossref |
| SourceType | Enrichment Source Index Database |
| StartPage | 1 |
| Subtitle | A Deep Network for Fake News Early Detection on Social Media |
| Title | FNED |
| Volume | 38 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bS8MwFA66gfgiXnHe2IP4Fm2apEsfx3QMcXtxg72N3AoDmTK7F3-9J026lil4eSklJKXJ137n5HK-g9C10uDmWiZxSonGTBKBJfxS2FouYrfrmxWiPsNRMpiwxymfVjk9i-iSXN3qj2_jSv6DKpQBri5K9g_Irh8KBXAP-MIVEIbrrzDujwLtlDKyvaHL-VAmAC92AoIyagHze02e3B3Cma8KBpbBejlu9iVz3IdCAL50wcO6QBxV55cClcHMF4M59uxmA71xGEHhE9mU_EdFDWdaIzNSs4pereIr3zInTQHTXJhG0cqklNvoG5Zmff7PR0PzWWi4jZoxePlAU83u_fDpuRbYmgQ5Cd8VH_Xsmt6FpjV3ouYXjPfRXnDo212PzgHasotDtFPGExyhhgPpGE36D-PeAIfUE1gDweWYqcgqaZTmUWyyiJhYMpEZnUSUUa0EvKxNlZYwNUm5lMSwJOsQktHE6VWTiJ6gxuJ1YU9R2wrDE6rTVII7pNyyXcwzYgTpdDLDNGmhm7IHMx102V16kJfZxii1UHtd8c1LkWxWOfu5yjnarb6WC9TIlyt7CX5Vrq7C6H8Cr_0c7A |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=FNED&rft.jtitle=ACM+transactions+on+information+systems&rft.au=Liu%2C+Yang&rft.au=Wu%2C+Yi-Fang+Brook&rft.date=2020-06-01&rft.issn=1046-8188&rft.eissn=1558-2868&rft.volume=38&rft.issue=3&rft.spage=1&rft.epage=33&rft_id=info:doi/10.1145%2F3386253&rft.externalDBID=n%2Fa&rft.externalDocID=10_1145_3386253 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1046-8188&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1046-8188&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1046-8188&client=summon |