Commit 2cfeda36d0ff90beb5d3b6b646530fcbbc4bc866

Authored by dsotofor
1 parent 12900f3599
Exists in main

version all ok, corrections to do in general conclusion...

Showing 10 changed files with 121 additions and 80 deletions Side-by-side Diff

No preview for this file type

chapters/Conclusions.aux View file @ 2cfeda3
... ... @@ -4,6 +4,8 @@
4 4 \@writefile{lof}{\addvspace {10\p@ }}
5 5 \@writefile{lot}{\addvspace {10\p@ }}
6 6 \@writefile{toc}{\contentsline {section}{\numberline {8.1}Conclusion générale}{103}{section.8.1}\protected@file@percent }
  7 +\citation{CHEN2025104070}
  8 +\citation{busch2023teaching}
7 9 \@writefile{toc}{\contentsline {section}{\numberline {8.2}Perspectives}{105}{section.8.2}\protected@file@percent }
8 10 \@setckpt{./chapters/Conclusions}{
9 11 \setcounter{page}{106}
chapters/Conclusions.tex View file @ 2cfeda3
... ... @@ -28,7 +28,7 @@
28 28  
29 29 \section{Perspectives}
30 30  
31   -Différentes évolutions peuvent être envisagées. En particulier, l'intégration de résultats d'analyse vidéo et audio pourrait aider à mieux interpréter les émotions et comportements des apprenants dans la séance et ainsi leur proposer des recommandations encore plus pertinentes. Il serait envisageable d'ajouter un module incluant une courbe d'oubli dynamique en suivant l'hypothèse d'Ebbinghaus \colorbox{yellow}{réf} avec une méthode telle que celle proposée dans le système de Leitner \colorbox{yellow}{ref}.
  31 +Différentes évolutions peuvent être envisagées. En particulier, l'intégration de résultats d'analyse vidéo et audio pourrait aider à mieux interpréter les émotions et comportements des apprenants dans la séance et ainsi leur proposer des recommandations encore plus pertinentes. Il serait envisageable d'ajouter un module incluant une courbe d'oubli dynamique en suivant l'hypothèse d'Ebbinghaus \cite{CHEN2025104070} avec une méthode telle que celle proposée dans le système de Leitner \cite{busch2023teaching}.
32 32  
33 33 Il pourrait également être intéressant de proposer différentes configurations pour le système de recommandation, en changeant les paramètres définis. Le point de départ pourrait consister à étudier la possibilité d'améliorer encore la fonction déterminant quelles sont les meilleures solutions proposées au second niveau d'empilement de l'outil d'ensemble (ESCBR-SMA). Il pourrait être intéressant de pouvoir paramétrer cette fonction, qu'AI-VT en propose plusieurs et qu'elles soient dépendantes du profil de l'apprenant et des matières enseignées.
34 34  
... ... @@ -50,7 +50,9 @@
50 50 \bibcite{Auer}{Auer et~al., 2021}
51 51 \bibcite{badier:hal-04092828}{Badier et~al., 2023}
52 52 \bibcite{BAKUROV2021100913}{Bakurov et~al., 2021}
  53 +\bibcite{busch2023teaching}{Busch et~al., 2023}
53 54 \bibcite{10.1007/978-3-642-15973-2_50}{Butdee and Tichkiewitch, 2011}
  55 +\bibcite{CHEN2025104070}{Chen et~al., 2025}
54 56 \bibcite{CHIU2023100118}{Chiu et~al., 2023}
55 57 \bibcite{cmc.2023.033417}{Choi et~al., 2023}
56 58 \bibcite{Riesbeck1989}{C.K. and R.C., 1989}
... ... @@ -57,12 +57,24 @@
57 57 \newblock Genetic programming for stacked generalization.
58 58 \newblock {\em Swarm and Evolutionary Computation}, 65:100913.
59 59  
  60 +\bibitem[Busch et~al., 2023]{busch2023teaching}
  61 +Busch, B., Watson, E., and Bogatchek, L. (2023).
  62 +\newblock {\em Teaching and Learning Illuminated: The Big Ideas, Illustrated}.
  63 +\newblock Taylor and Francis.
  64 +
60 65 \bibitem[Butdee and Tichkiewitch, 2011]{10.1007/978-3-642-15973-2_50}
61 66 Butdee, S. and Tichkiewitch, S. (2011).
62 67 \newblock Case-based reasoning for adaptive aluminum extrusion die design
63 68 together with parameters by neural networks.
64 69 \newblock In Bernard, A., editor, {\em Global Product Development}, pages
65 70 491--496, Berlin, Heidelberg. Springer Berlin Heidelberg.
  71 +
  72 +\bibitem[Chen et~al., 2025]{CHEN2025104070}
  73 +Chen, H., Feng, Z., Chen, S., Wu, H., Sun, Y., Li, J., Gao, Q., Zhang, L., and
  74 + Xue, X. (2025).
  75 +\newblock Incorporating forgetting curve and memory replay for evolving
  76 + socially-aware recommendation.
  77 +\newblock {\em Information Processing and Management}, 62(3):104070.
66 78  
67 79 \bibitem[Chiu et~al., 2023]{CHIU2023100118}
68 80 Chiu, T.~K., Xia, Q., Zhou, X., Chai, C.~S., and Cheng, M. (2023).
... ... @@ -1807,4 +1807,29 @@
1807 1807 year={2023},
1808 1808 note = {Accessed: 2023-11-20}
1809 1809 }
  1810 +
  1811 +@article{CHEN2025104070,
  1812 +title = {Incorporating Forgetting Curve and Memory Replay for Evolving Socially-aware Recommendation},
  1813 +journal = {Information Processing and Management},
  1814 +volume = {62},
  1815 +number = {3},
  1816 +pages = {104070},
  1817 +year = {2025},
  1818 +issn = {0306-4573},
  1819 +doi = {https://doi.org/10.1016/j.ipm.2025.104070},
  1820 +url = {https://www.sciencedirect.com/science/article/pii/S0306457325000123},
  1821 +author = {Hongqi Chen and Zhiyong Feng and Shizhan Chen and Hongyue Wu and Yingchao Sun and Jingyu Li and Qinghang Gao and Lu Zhang and Xiao Xue},
  1822 +keywords = {Social recommendation, Forgetting curve, Memory replay, Social consistency, Graph neural networks},
  1823 +abstract = {Social recommendations play a crucial role in helping users filter information and discover potential requirements. However, existing works often ignore the effects of memory patterns and social inconsistency, which hide the recommendation for capturing evolving user interests. To overcome these problems, a model incorporating the Forgetting curve and Memory Replay for Evolving Socially-aware recommendation (FMRES) is proposed to navigate users’ fresh interests. Specifically, a cognitive-inspired Ebbinghaus curve is integrated with item attributes to consider users’ personalized interest forgetting and retention. Then, the memory replay mechanism is employed to revive forgotten yet valuable items, fostering user engagement and enhancing relevance in recommendations. By aggregating the neighbors’ social characters, consistent friends are sampled to identify meaningful and impactful relationships. Finally, temporal representations of users and items are incorporated to track the evolution of users’ interests by utilizing gated recurrent units. Extensive experiments on three datasets demonstrate that the proposed model consistently outperforms advanced baseline methods over various metrics.}
  1824 +}
  1825 +
  1826 +@book{busch2023teaching,
  1827 + title={Teaching and Learning Illuminated: The Big Ideas, Illustrated},
  1828 + author={Busch, B. and Watson, E. and Bogatchek, L.},
  1829 + isbn={9781000877960},
  1830 + lccn={2022056096},
  1831 + url={https://books.google.fr/books?id=ik-3EAAAQBAJ},
  1832 + year={2023},
  1833 + publisher={Taylor and Francis}
  1834 +}
... ... @@ -15,46 +15,46 @@
15 15 --line 693 of file main.bib
16 16 Warning--to sort, need author or key in UCI
17 17 Warning--to sort, need author or key in Data
18   -You've used 85 entries,
  18 +You've used 87 entries,
19 19 1935 wiz_defined-function locations,
20   - 1005 strings with 21157 characters,
21   -and the built_in function-call counts, 38168 in all, are:
22   -= -- 3659
23   -> -- 1794
  20 + 1016 strings with 21593 characters,
  21 +and the built_in function-call counts, 39102 in all, are:
  22 += -- 3739
  23 +> -- 1860
24 24 < -- 56
25   -+ -- 656
26   -- -- 602
27   -* -- 3272
28   -:= -- 6527
29   -add.period$ -- 274
30   -call.type$ -- 85
31   -change.case$ -- 701
32   -chr.to.int$ -- 83
33   -cite$ -- 89
34   -duplicate$ -- 1442
35   -empty$ -- 2581
36   -format.name$ -- 731
37   -if$ -- 7600
  25 ++ -- 680
  26 +- -- 626
  27 +* -- 3362
  28 +:= -- 6698
  29 +add.period$ -- 280
  30 +call.type$ -- 87
  31 +change.case$ -- 722
  32 +chr.to.int$ -- 85
  33 +cite$ -- 91
  34 +duplicate$ -- 1470
  35 +empty$ -- 2633
  36 +format.name$ -- 757
  37 +if$ -- 7773
38 38 int.to.chr$ -- 3
39 39 int.to.str$ -- 0
40   -missing$ -- 88
41   -newline$ -- 430
42   -num.names$ -- 279
43   -pop$ -- 632
  40 +missing$ -- 91
  41 +newline$ -- 440
  42 +num.names$ -- 285
  43 +pop$ -- 655
44 44 preamble$ -- 1
45   -purify$ -- 706
  45 +purify$ -- 728
46 46 quote$ -- 0
47   -skip$ -- 1101
  47 +skip$ -- 1120
48 48 stack$ -- 0
49   -substring$ -- 2563
50   -swap$ -- 270
  49 +substring$ -- 2605
  50 +swap$ -- 272
51 51 text.length$ -- 24
52 52 text.prefix$ -- 0
53 53 top$ -- 0
54   -type$ -- 498
  54 +type$ -- 508
55 55 warning$ -- 2
56   -while$ -- 284
  56 +while$ -- 289
57 57 width$ -- 0
58   -write$ -- 1135
  58 +write$ -- 1160
59 59 (There were 3 warnings)
1   -This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) (preloaded format=pdflatex 2023.5.31) 16 JUL 2025 14:43
  1 +This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) (preloaded format=pdflatex 2023.5.31) 16 JUL 2025 15:34
2 2 entering extended mode
3 3 restricted \write18 enabled.
4 4 %&-line parsing enabled.
5 5  
6 6  
... ... @@ -2068,18 +2068,18 @@
2068 2068  
2069 2069  
2070 2070 ]
2071   -Underfull \hbox (badness 1394) in paragraph at lines 131--137
  2071 +Underfull \hbox (badness 1394) in paragraph at lines 143--149
2072 2072 []\T1/phv/m/n/10.95 Henriet, J., Chris-tophe, L., and Laurent, P. (2017). Ar-t
2073 2073 i-fi-cial
2074 2074 []
2075 2075  
2076 2076 [110] [111]
2077   -Underfull \hbox (badness 1939) in paragraph at lines 295--299
  2077 +Underfull \hbox (badness 1939) in paragraph at lines 307--311
2078 2078 []\T1/phv/m/n/10.95 Muangprathub, J., Boon-jing, V., and Cham-nong-thai, K.
2079 2079 []
2080 2080  
2081 2081  
2082   -Underfull \hbox (badness 2452) in paragraph at lines 346--350
  2082 +Underfull \hbox (badness 2452) in paragraph at lines 358--362
2083 2083 []\T1/phv/m/n/10.95 Petrovic, S., Khus-sai-nova, G., and Ja-gan-na-than, R. (20
2084 2084 16).
2085 2085 []
... ... @@ -2097,7 +2097,7 @@
2097 2097 pdfTeX warning: /Library/TeX/texbin/pdflatex (file ./spimufcphdthesis-backpage.
2098 2098 pdf): PDF inclusion: found PDF version <1.7>, but at most version <1.5> allowed
2099 2099  
2100   -<spimufcphdthesis-backpage.pdf, id=1678, 597.6729pt x 845.07718pt>
  2100 +<spimufcphdthesis-backpage.pdf, id=1682, 597.6729pt x 845.07718pt>
2101 2101 File: spimufcphdthesis-backpage.pdf Graphic file (type pdf)
2102 2102 <use spimufcphdthesis-backpage.pdf>
2103 2103 Package pdftex.def Info: spimufcphdthesis-backpage.pdf used on input line 389.
2104 2104  
... ... @@ -2125,10 +2125,10 @@
2125 2125 (rerunfilecheck) Checksum: 4D23690A3BB32D8DF3C92F3F5BF35324;24241.
2126 2126 )
2127 2127 Here is how much of TeX's memory you used:
2128   - 21554 strings out of 476038
2129   - 369970 string characters out of 5790170
  2128 + 21558 strings out of 476038
  2129 + 370046 string characters out of 5790170
2130 2130 1902785 words of memory out of 5000000
2131   - 40973 multiletter control sequences out of 15000+600000
  2131 + 40975 multiletter control sequences out of 15000+600000
2132 2132 619032 words of font info for 151 fonts, out of 8000000 for 9000
2133 2133 1141 hyphenation exceptions out of 8191
2134 2134 126i,17n,133p,1979b,754s stack positions out of 10000i,1000n,20000p,200000b,200000s
2135 2135  
... ... @@ -2159,10 +2159,10 @@
2159 2159 lvetic/uhvr8a.pfb></usr/local/texlive/2023/texmf-dist/fonts/type1/urw/helvetic/
2160 2160 uhvro8a.pfb></usr/local/texlive/2023/texmf-dist/fonts/type1/urw/times/utmr8a.pf
2161 2161 b></usr/local/texlive/2023/texmf-dist/fonts/type1/urw/times/utmri8a.pfb>
2162   -Output written on main.pdf (124 pages, 5444371 bytes).
  2162 +Output written on main.pdf (124 pages, 5444983 bytes).
2163 2163 PDF statistics:
2164   - 1844 PDF objects out of 2073 (max. 8388607)
2165   - 1575 compressed objects within 16 object streams
2166   - 462 named destinations out of 1000 (max. 500000)
  2164 + 1849 PDF objects out of 2073 (max. 8388607)
  2165 + 1580 compressed objects within 16 object streams
  2166 + 464 named destinations out of 1000 (max. 500000)
2167 2167 1006 words of extra memory for PDF output out of 10000 (max. 10000000)

No preview for this file type

main.synctex.gz View file @ 2cfeda3

No preview for this file type