Document (#39680)

Author

Gemmis, M. de
Lops, P.
Semeraro, G.
Musto, C.

Title

¬An investigation on the serendipity problem in recommender systems

Source

Information processing and management. 51(2015) no.5, S.695-717

Year

2015

Abstract

Recommender systems are filters which suggest items or information that might be interesting to users. These systems analyze the past behavior of a user, build her profile that stores information about her interests, and exploit that profile to find potentially interesting items. The main limitation of this approach is that it may provide accurate but likely obvious suggestions, since recommended items are similar to those the user already knows. In this paper we investigate this issue, known as overspecialization or serendipity problem, by proposing a strategy that fosters the suggestion of surprisingly interesting items the user might not have otherwise discovered. The proposed strategy enriches a graph-based recommendation algorithm with background knowledge that allows the system to deeply understand the items it deals with. The hypothesis is that the infused knowledge could help to discover hidden correlations among items that go beyond simple feature similarity and therefore promote non-obvious suggestions. Two evaluations are performed to validate this hypothesis: an in vitro experiment on a subset of the hetrec2011-movielens-2k dataset, and a preliminary user study. Those evaluations show that the proposed strategy actually promotes non-obvious suggestions, by narrowing the accuracy loss.

Content

Vgl.: doi: 10.1016/j.ipm.2015.06.008.

Similar documents (content)

1. Smets, A.; Vannieuwenhuyze, J.; Ballon, P.: Serendipity in the city : user evaluations of urban recommender systems (2022) 0.34

   0.33696836 = sum of:
     0.33696836 = product of:
       0.9360232 = sum of:
         0.01902448 = weight(abstract_txt:this in 458) [ClassicSimilarity], result of:
           0.01902448 = score(doc=458,freq=6.0), product of:
             0.05149875 = queryWeight, product of:
               1.1976311 = boost
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.017820222 = queryNorm
             0.36941636 = fieldWeight in 458, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.028520571 = weight(abstract_txt:systems in 458) [ClassicSimilarity], result of:
           0.028520571 = score(doc=458,freq=3.0), product of:
             0.07721898 = queryWeight, product of:
               1.2700399 = boost
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.017820222 = queryNorm
             0.36934665 = fieldWeight in 458, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.07683294 = weight(abstract_txt:profile in 458) [ClassicSimilarity], result of:
           0.07683294 = score(doc=458,freq=1.0), product of:
             0.1883621 = queryWeight, product of:
               1.6195953 = boost
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.017820222 = queryNorm
             0.4079002 = fieldWeight in 458, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.5264034 = idf(docFreq=175, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.08286605 = weight(abstract_txt:evaluations in 458) [ClassicSimilarity], result of:
           0.08286605 = score(doc=458,freq=1.0), product of:
             0.1980978 = queryWeight, product of:
               1.6609232 = boost
               6.6929407 = idf(docFreq=148, maxDocs=44218)
               0.017820222 = queryNorm
             0.4183088 = fieldWeight in 458, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.6929407 = idf(docFreq=148, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.03907225 = weight(abstract_txt:user in 458) [ClassicSimilarity], result of:
           0.03907225 = score(doc=458,freq=2.0), product of:
             0.120007254 = queryWeight, product of:
               1.8282201 = boost
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.017820222 = queryNorm
             0.32558239 = fieldWeight in 458, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.25834846 = weight(abstract_txt:serendipity in 458) [ClassicSimilarity], result of:
           0.25834846 = score(doc=458,freq=3.0), product of:
             0.29312897 = queryWeight, product of:
               2.0204082 = boost
               8.14154 = idf(docFreq=34, maxDocs=44218)
               0.017820222 = queryNorm
             0.8813475 = fieldWeight in 458, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               8.14154 = idf(docFreq=34, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.26399043 = weight(abstract_txt:recommender in 458) [ClassicSimilarity], result of:
           0.26399043 = score(doc=458,freq=3.0), product of:
             0.29738128 = queryWeight, product of:
               2.03501 = boost
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.017820222 = queryNorm
             0.88771707 = fieldWeight in 458, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.023399668 = weight(abstract_txt:that in 458) [ClassicSimilarity], result of:
           0.023399668 = score(doc=458,freq=2.0), product of:
             0.11172813 = queryWeight, product of:
               2.6460452 = boost
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.017820222 = queryNorm
             0.20943399 = fieldWeight in 458, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
         0.14396836 = weight(abstract_txt:items in 458) [ClassicSimilarity], result of:
           0.14396836 = score(doc=458,freq=1.0), product of:
             0.41290203 = queryWeight, product of:
               4.1533055 = boost
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.017820222 = queryNorm
             0.3486744 = fieldWeight in 458, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.0625 = fieldNorm(doc=458)
       0.36 = coord(9/25)
   

2. Ackerman, B.; Wang, C.; Chen, Y.: ¬A session-specific opportunity cost model for rank-oriented recommendation (2018) 0.20

   0.2047233 = sum of:
     0.2047233 = product of:
       0.7311546 = sum of:
         0.030661995 = weight(abstract_txt:problem in 4468) [ClassicSimilarity], result of:
           0.030661995 = score(doc=4468,freq=1.0), product of:
             0.087987736 = queryWeight, product of:
               1.1069317 = boost
               4.460548 = idf(docFreq=1388, maxDocs=44218)
               0.017820222 = queryNorm
             0.3484803 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.460548 = idf(docFreq=1388, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
         0.009708389 = weight(abstract_txt:this in 4468) [ClassicSimilarity], result of:
           0.009708389 = score(doc=4468,freq=1.0), product of:
             0.05149875 = queryWeight, product of:
               1.1976311 = boost
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.017820222 = queryNorm
             0.18851699 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
         0.02058295 = weight(abstract_txt:systems in 4468) [ClassicSimilarity], result of:
           0.02058295 = score(doc=4468,freq=1.0), product of:
             0.07721898 = queryWeight, product of:
               1.2700399 = boost
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.017820222 = queryNorm
             0.26655298 = fieldWeight in 4468, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
         0.059816916 = weight(abstract_txt:user in 4468) [ClassicSimilarity], result of:
           0.059816916 = score(doc=4468,freq=3.0), product of:
             0.120007254 = queryWeight, product of:
               1.8282201 = boost
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.017820222 = queryNorm
             0.49844417 = fieldWeight in 4468, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
         0.26943412 = weight(abstract_txt:recommender in 4468) [ClassicSimilarity], result of:
           0.26943412 = score(doc=4468,freq=2.0), product of:
             0.29738128 = queryWeight, product of:
               2.03501 = boost
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.017820222 = queryNorm
             0.9060225 = fieldWeight in 4468, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
         0.029249584 = weight(abstract_txt:that in 4468) [ClassicSimilarity], result of:
           0.029249584 = score(doc=4468,freq=2.0), product of:
             0.11172813 = queryWeight, product of:
               2.6460452 = boost
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.017820222 = queryNorm
             0.26179248 = fieldWeight in 4468, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
         0.31170067 = weight(abstract_txt:items in 4468) [ClassicSimilarity], result of:
           0.31170067 = score(doc=4468,freq=3.0), product of:
             0.41290203 = queryWeight, product of:
               4.1533055 = boost
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.017820222 = queryNorm
             0.75490224 = fieldWeight in 4468, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.078125 = fieldNorm(doc=4468)
       0.28 = coord(7/25)
   

3. Hansen, D.L.; Khopkar, T.; Zhang, J.: Recommender systems and expert locators (2009) 0.16

   0.16092251 = sum of:
     0.16092251 = product of:
       0.8046126 = sum of:
         0.011650068 = weight(abstract_txt:this in 3867) [ClassicSimilarity], result of:
           0.011650068 = score(doc=3867,freq=1.0), product of:
             0.05149875 = queryWeight, product of:
               1.1976311 = boost
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.017820222 = queryNorm
             0.2262204 = fieldWeight in 3867, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.09375 = fieldNorm(doc=3867)
         0.060501277 = weight(abstract_txt:systems in 3867) [ClassicSimilarity], result of:
           0.060501277 = score(doc=3867,freq=6.0), product of:
             0.07721898 = queryWeight, product of:
               1.2700399 = boost
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.017820222 = queryNorm
             0.7835027 = fieldWeight in 3867, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.09375 = fieldNorm(doc=3867)
         0.32332096 = weight(abstract_txt:recommender in 3867) [ClassicSimilarity], result of:
           0.32332096 = score(doc=3867,freq=2.0), product of:
             0.29738128 = queryWeight, product of:
               2.03501 = boost
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.017820222 = queryNorm
             1.087227 = fieldWeight in 3867, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.200379 = idf(docFreq=32, maxDocs=44218)
               0.09375 = fieldNorm(doc=3867)
         0.035099503 = weight(abstract_txt:that in 3867) [ClassicSimilarity], result of:
           0.035099503 = score(doc=3867,freq=2.0), product of:
             0.11172813 = queryWeight, product of:
               2.6460452 = boost
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.017820222 = queryNorm
             0.314151 = fieldWeight in 3867, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.09375 = fieldNorm(doc=3867)
         0.37404078 = weight(abstract_txt:items in 3867) [ClassicSimilarity], result of:
           0.37404078 = score(doc=3867,freq=3.0), product of:
             0.41290203 = queryWeight, product of:
               4.1533055 = boost
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.017820222 = queryNorm
             0.90588266 = fieldWeight in 3867, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.09375 = fieldNorm(doc=3867)
       0.2 = coord(5/25)
   

4. Marshall, B.; Chen, H.; Kaza, S.: Using importance flooding to identify interesting networks of criminal activity (2008) 0.14

   0.14398219 = sum of:
     0.14398219 = product of:
       0.5142221 = sum of:
         0.03827802 = weight(abstract_txt:proposed in 2386) [ClassicSimilarity], result of:
           0.03827802 = score(doc=2386,freq=2.0), product of:
             0.09395463 = queryWeight, product of:
               1.1438494 = boost
               4.6093135 = idf(docFreq=1196, maxDocs=44218)
               0.017820222 = queryNorm
             0.4074096 = fieldWeight in 2386, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.6093135 = idf(docFreq=1196, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
         0.010983788 = weight(abstract_txt:this in 2386) [ClassicSimilarity], result of:
           0.010983788 = score(doc=2386,freq=2.0), product of:
             0.05149875 = queryWeight, product of:
               1.1976311 = boost
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.017820222 = queryNorm
             0.21328263 = fieldWeight in 2386, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
         0.03907225 = weight(abstract_txt:user in 2386) [ClassicSimilarity], result of:
           0.03907225 = score(doc=2386,freq=2.0), product of:
             0.120007254 = queryWeight, product of:
               1.8282201 = boost
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.017820222 = queryNorm
             0.32558239 = fieldWeight in 2386, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
         0.12620822 = weight(abstract_txt:suggestions in 2386) [ClassicSimilarity], result of:
           0.12620822 = score(doc=2386,freq=2.0), product of:
             0.2382543 = queryWeight, product of:
               2.2308776 = boost
               5.993105 = idf(docFreq=299, maxDocs=44218)
               0.017820222 = queryNorm
             0.5297206 = fieldWeight in 2386, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.993105 = idf(docFreq=299, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
         0.13916542 = weight(abstract_txt:interesting in 2386) [ClassicSimilarity], result of:
           0.13916542 = score(doc=2386,freq=2.0), product of:
             0.25429425 = queryWeight, product of:
               2.304749 = boost
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.017820222 = queryNorm
             0.54726136 = fieldWeight in 2386, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               6.1915555 = idf(docFreq=245, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
         0.016546065 = weight(abstract_txt:that in 2386) [ClassicSimilarity], result of:
           0.016546065 = score(doc=2386,freq=1.0), product of:
             0.11172813 = queryWeight, product of:
               2.6460452 = boost
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.017820222 = queryNorm
             0.1480922 = fieldWeight in 2386, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
         0.14396836 = weight(abstract_txt:items in 2386) [ClassicSimilarity], result of:
           0.14396836 = score(doc=2386,freq=1.0), product of:
             0.41290203 = queryWeight, product of:
               4.1533055 = boost
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.017820222 = queryNorm
             0.3486744 = fieldWeight in 2386, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.0625 = fieldNorm(doc=2386)
       0.28 = coord(7/25)
   

5. Soledad Pera, M.; Ng, Y.-K.: Recommending books to be exchanged online in the absence of wish lists (2018) 0.14

   0.1432812 = sum of:
     0.1432812 = product of:
       0.59700507 = sum of:
         0.0077667115 = weight(abstract_txt:this in 4182) [ClassicSimilarity], result of:
           0.0077667115 = score(doc=4182,freq=1.0), product of:
             0.05149875 = queryWeight, product of:
               1.1976311 = boost
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.017820222 = queryNorm
             0.1508136 = fieldWeight in 4182, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4130175 = idf(docFreq=10762, maxDocs=44218)
               0.0625 = fieldNorm(doc=4182)
         0.02328695 = weight(abstract_txt:systems in 4182) [ClassicSimilarity], result of:
           0.02328695 = score(doc=4182,freq=2.0), product of:
             0.07721898 = queryWeight, product of:
               1.2700399 = boost
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.017820222 = queryNorm
             0.3015703 = fieldWeight in 4182, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.4118783 = idf(docFreq=3963, maxDocs=44218)
               0.0625 = fieldNorm(doc=4182)
         0.06177865 = weight(abstract_txt:user in 4182) [ClassicSimilarity], result of:
           0.06177865 = score(doc=4182,freq=5.0), product of:
             0.120007254 = queryWeight, product of:
               1.8282201 = boost
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.017820222 = queryNorm
             0.51479095 = fieldWeight in 4182, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               3.6835442 = idf(docFreq=3020, maxDocs=44218)
               0.0625 = fieldNorm(doc=4182)
         0.14915757 = weight(abstract_txt:serendipity in 4182) [ClassicSimilarity], result of:
           0.14915757 = score(doc=4182,freq=1.0), product of:
             0.29312897 = queryWeight, product of:
               2.0204082 = boost
               8.14154 = idf(docFreq=34, maxDocs=44218)
               0.017820222 = queryNorm
             0.5088462 = fieldWeight in 4182, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.14154 = idf(docFreq=34, maxDocs=44218)
               0.0625 = fieldNorm(doc=4182)
         0.03309213 = weight(abstract_txt:that in 4182) [ClassicSimilarity], result of:
           0.03309213 = score(doc=4182,freq=4.0), product of:
             0.11172813 = queryWeight, product of:
               2.6460452 = boost
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.017820222 = queryNorm
             0.2961844 = fieldWeight in 4182, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.3694751 = idf(docFreq=11241, maxDocs=44218)
               0.0625 = fieldNorm(doc=4182)
         0.32192305 = weight(abstract_txt:items in 4182) [ClassicSimilarity], result of:
           0.32192305 = score(doc=4182,freq=5.0), product of:
             0.41290203 = queryWeight, product of:
               4.1533055 = boost
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.017820222 = queryNorm
             0.7796596 = fieldWeight in 4182, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               5.57879 = idf(docFreq=453, maxDocs=44218)
               0.0625 = fieldNorm(doc=4182)
       0.24 = coord(6/25)