Document (#43090)

Author

Singh, V.K.
Ghosh, I.
Sonagara, D.

Title

Detecting fake news stories via multimodal analysis

Source

Journal of the Association for Information Science and Technology. 72(2021) no.1, S.3-17

Year

2021

Abstract

Filtering, vetting, and verifying digital information is an area of core interest in information science. Online fake news is a specific type of digital misinformation that poses serious threats to democratic institutions, misguides the public, and can lead to radicalization and violence. Hence, fake news detection is an important problem for information science research. While there have been multiple attempts to identify fake news, most of such efforts have focused on a single modality (e.g., only text-based or only visual features). However, news articles are increasingly framed as multimodal news stories, and hence, in this work, we propose a multimodal approach combining text and visual analysis of online news stories to automatically detect fake news. Drawing on key theories of information processing and presentation, we identify multiple text and visual features that are associated with fake or credible news articles. We then perform a predictive analysis to detect features most strongly associated with fake news. Next, we combine these features in predictive models using multiple machine-learning techniques. The experimental results indicate that a multimodal approach outperforms single-modality approaches, allowing for better fake news detection.

Content

Vgl.: https://asistdl.onlinelibrary.wiley.com/doi/10.1002/asi.24359.

Similar documents (author)

1. Ghosh, I.; Singh, V.: "Not all my friends are friends" : audience-group-based nudges for managing location privacy (2022) 6.23

   6.229343 = sum of:
     6.229343 = sum of:
       2.7691405 = weight(author_txt:singh in 1562) [ClassicSimilarity], result of:
         2.7691405 = score(doc=1562,freq=1.0), product of:
           0.6528996 = queryWeight, product of:
             8.482592 = idf(docFreq=24, maxDocs=44421)
             0.076969355 = queryNorm
           4.241296 = fieldWeight in 1562, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             8.482592 = idf(docFreq=24, maxDocs=44421)
             0.5 = fieldNorm(doc=1562)
       3.4602025 = weight(author_txt:ghosh in 1562) [ClassicSimilarity], result of:
         3.4602025 = score(doc=1562,freq=1.0), product of:
           0.75744444 = queryWeight, product of:
             1.0770905 = boost
             9.1365185 = idf(docFreq=12, maxDocs=44421)
             0.076969355 = queryNorm
           4.5682592 = fieldWeight in 1562, product of:
             1.0 = tf(freq=1.0), with freq of:
               1.0 = termFreq=1.0
             9.1365185 = idf(docFreq=12, maxDocs=44421)
             0.5 = fieldNorm(doc=1562)
   

2. Ghosh, S.P.: Statistical databases : design of experiment structures (1993) 2.16

   2.1626267 = sum of:
     2.1626267 = product of:
       4.3252535 = sum of:
         4.3252535 = weight(author_txt:ghosh in 6741) [ClassicSimilarity], result of:
           4.3252535 = score(doc=6741,freq=1.0), product of:
             0.75744444 = queryWeight, product of:
               1.0770905 = boost
               9.1365185 = idf(docFreq=12, maxDocs=44421)
               0.076969355 = queryNorm
             5.7103243 = fieldWeight in 6741, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.1365185 = idf(docFreq=12, maxDocs=44421)
               0.625 = fieldNorm(doc=6741)
       0.5 = coord(1/2)
   

3. Ghosh, S.B.: ¬A new paradigm of education system for reaching the unreached through open and distance education with special reference to the Indian initiative (2006) 2.16

   2.1626267 = sum of:
     2.1626267 = product of:
       4.3252535 = sum of:
         4.3252535 = weight(author_txt:ghosh in 2509) [ClassicSimilarity], result of:
           4.3252535 = score(doc=2509,freq=1.0), product of:
             0.75744444 = queryWeight, product of:
               1.0770905 = boost
               9.1365185 = idf(docFreq=12, maxDocs=44421)
               0.076969355 = queryNorm
             5.7103243 = fieldWeight in 2509, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.1365185 = idf(docFreq=12, maxDocs=44421)
               0.625 = fieldNorm(doc=2509)
       0.5 = coord(1/2)
   

4. Singh, S.: From reference to information services : a study on impact of Ranganathan (1992) 1.73

   1.7307127 = sum of:
     1.7307127 = product of:
       3.4614253 = sum of:
         3.4614253 = weight(author_txt:singh in 6696) [ClassicSimilarity], result of:
           3.4614253 = score(doc=6696,freq=1.0), product of:
             0.6528996 = queryWeight, product of:
               8.482592 = idf(docFreq=24, maxDocs=44421)
               0.076969355 = queryNorm
             5.3016195 = fieldWeight in 6696, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.482592 = idf(docFreq=24, maxDocs=44421)
               0.625 = fieldNorm(doc=6696)
       0.5 = coord(1/2)
   

5. Singh, S.: S.R. Ranganathan : a review of centenary celebration events and literature (1994) 1.73

   1.7307127 = sum of:
     1.7307127 = product of:
       3.4614253 = sum of:
         3.4614253 = weight(author_txt:singh in 761) [ClassicSimilarity], result of:
           3.4614253 = score(doc=761,freq=1.0), product of:
             0.6528996 = queryWeight, product of:
               8.482592 = idf(docFreq=24, maxDocs=44421)
               0.076969355 = queryNorm
             5.3016195 = fieldWeight in 761, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.482592 = idf(docFreq=24, maxDocs=44421)
               0.625 = fieldNorm(doc=761)
       0.5 = coord(1/2)
   

Similar documents (content)

1. Affelt, A.: All that's not fit to print : fake news and the call to action for librarians and information professionals (2019) 0.27

   0.2688736 = sum of:
     0.2688736 = product of:
       1.344368 = sum of:
         0.011840587 = weight(abstract_txt:only in 1103) [ClassicSimilarity], result of:
           0.011840587 = score(doc=1103,freq=1.0), product of:
             0.044725634 = queryWeight, product of:
               1.0033462 = boost
               4.235812 = idf(docFreq=1746, maxDocs=44421)
               0.010523713 = queryNorm
             0.26473826 = fieldWeight in 1103, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.235812 = idf(docFreq=1746, maxDocs=44421)
               0.0625 = fieldNorm(doc=1103)
         0.008820163 = weight(abstract_txt:information in 1103) [ClassicSimilarity], result of:
           0.008820163 = score(doc=1103,freq=4.0), product of:
             0.02917083 = queryWeight, product of:
               1.1459402 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.010523713 = queryNorm
             0.30236244 = fieldWeight in 1103, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=1103)
         0.0113237 = weight(abstract_txt:analysis in 1103) [ClassicSimilarity], result of:
           0.0113237 = score(doc=1103,freq=1.0), product of:
             0.04969702 = queryWeight, product of:
               1.2953387 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010523713 = queryNorm
             0.2278547 = fieldWeight in 1103, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.0625 = fieldNorm(doc=1103)
         0.8327849 = weight(abstract_txt:fake in 1103) [ClassicSimilarity], result of:
           0.8327849 = score(doc=1103,freq=7.0), product of:
             0.63238794 = queryWeight, product of:
               7.54561 = boost
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.010523713 = queryNorm
             1.3168893 = fieldWeight in 1103, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.0625 = fieldNorm(doc=1103)
         0.47959867 = weight(abstract_txt:news in 1103) [ClassicSimilarity], result of:
           0.47959867 = score(doc=1103,freq=7.0), product of:
             0.48675966 = queryWeight, product of:
               7.7626715 = boost
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.010523713 = queryNorm
             0.98528844 = fieldWeight in 1103, product of:
               2.6457512 = tf(freq=7.0), with freq of:
                 7.0 = termFreq=7.0
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.0625 = fieldNorm(doc=1103)
       0.2 = coord(5/25)
   

2. Giachanou, A.; Rosso, P.; Crestani, F.: ¬The impact of emotional signals on credibility assessment (2021) 0.24

   0.24345194 = sum of:
     0.24345194 = product of:
       1.0143831 = sum of:
         0.07535949 = weight(abstract_txt:credible in 1329) [ClassicSimilarity], result of:
           0.07535949 = score(doc=1329,freq=2.0), product of:
             0.09676383 = queryWeight, product of:
               1.0435519 = boost
               8.811096 = idf(docFreq=17, maxDocs=44421)
               0.010523713 = queryNorm
             0.7787982 = fieldWeight in 1329, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.811096 = idf(docFreq=17, maxDocs=44421)
               0.0625 = fieldNorm(doc=1329)
         0.016014129 = weight(abstract_txt:analysis in 1329) [ClassicSimilarity], result of:
           0.016014129 = score(doc=1329,freq=2.0), product of:
             0.04969702 = queryWeight, product of:
               1.2953387 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010523713 = queryNorm
             0.3222352 = fieldWeight in 1329, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.0625 = fieldNorm(doc=1329)
         0.01541995 = weight(abstract_txt:text in 1329) [ClassicSimilarity], result of:
           0.01541995 = score(doc=1329,freq=1.0), product of:
             0.061055776 = queryWeight, product of:
               1.4357591 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.010523713 = queryNorm
             0.25255513 = fieldWeight in 1329, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.0625 = fieldNorm(doc=1329)
         0.04843283 = weight(abstract_txt:detection in 1329) [ClassicSimilarity], result of:
           0.04843283 = score(doc=1329,freq=1.0), product of:
             0.11439339 = queryWeight, product of:
               1.6046231 = boost
               6.774214 = idf(docFreq=137, maxDocs=44421)
               0.010523713 = queryNorm
             0.42338836 = fieldWeight in 1329, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               6.774214 = idf(docFreq=137, maxDocs=44421)
               0.0625 = fieldNorm(doc=1329)
         0.5451857 = weight(abstract_txt:fake in 1329) [ClassicSimilarity], result of:
           0.5451857 = score(doc=1329,freq=3.0), product of:
             0.63238794 = queryWeight, product of:
               7.54561 = boost
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.010523713 = queryNorm
             0.8621064 = fieldWeight in 1329, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.963798 = idf(docFreq=41, maxDocs=44421)
               0.0625 = fieldNorm(doc=1329)
         0.313971 = weight(abstract_txt:news in 1329) [ClassicSimilarity], result of:
           0.313971 = score(doc=1329,freq=3.0), product of:
             0.48675966 = queryWeight, product of:
               7.7626715 = boost
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.010523713 = queryNorm
             0.6450227 = fieldWeight in 1329, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.0625 = fieldNorm(doc=1329)
       0.24 = coord(6/25)
   

3. Hansen, K.A.: Local breaking news : sources, technology, and new routines (1994) 0.18

   0.17723975 = sum of:
     0.17723975 = product of:
       0.738499 = sum of:
         0.011457727 = weight(abstract_txt:information in 1678) [ClassicSimilarity], result of:
           0.011457727 = score(doc=1678,freq=3.0), product of:
             0.02917083 = queryWeight, product of:
               1.1459402 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.010523713 = queryNorm
             0.3927803 = fieldWeight in 1678, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.09375 = fieldNorm(doc=1678)
         0.027936019 = weight(abstract_txt:identify in 1678) [ClassicSimilarity], result of:
           0.027936019 = score(doc=1678,freq=1.0), product of:
             0.060490876 = queryWeight, product of:
               1.1668566 = boost
               4.9261017 = idf(docFreq=875, maxDocs=44421)
               0.010523713 = queryNorm
             0.46182203 = fieldWeight in 1678, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.9261017 = idf(docFreq=875, maxDocs=44421)
               0.09375 = fieldNorm(doc=1678)
         0.024021192 = weight(abstract_txt:analysis in 1678) [ClassicSimilarity], result of:
           0.024021192 = score(doc=1678,freq=2.0), product of:
             0.04969702 = queryWeight, product of:
               1.2953387 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010523713 = queryNorm
             0.48335278 = fieldWeight in 1678, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.09375 = fieldNorm(doc=1678)
         0.04741965 = weight(abstract_txt:multiple in 1678) [ClassicSimilarity], result of:
           0.04741965 = score(doc=1678,freq=1.0), product of:
             0.09853326 = queryWeight, product of:
               1.8239361 = boost
               5.1333895 = idf(docFreq=711, maxDocs=44421)
               0.010523713 = queryNorm
             0.48125526 = fieldWeight in 1678, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.1333895 = idf(docFreq=711, maxDocs=44421)
               0.09375 = fieldNorm(doc=1678)
         0.24312998 = weight(abstract_txt:stories in 1678) [ClassicSimilarity], result of:
           0.24312998 = score(doc=1678,freq=3.0), product of:
             0.2031402 = queryWeight, product of:
               2.6188831 = boost
               7.370734 = idf(docFreq=75, maxDocs=44421)
               0.010523713 = queryNorm
             1.196858 = fieldWeight in 1678, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               7.370734 = idf(docFreq=75, maxDocs=44421)
               0.09375 = fieldNorm(doc=1678)
         0.38453442 = weight(abstract_txt:news in 1678) [ClassicSimilarity], result of:
           0.38453442 = score(doc=1678,freq=2.0), product of:
             0.48675966 = queryWeight, product of:
               7.7626715 = boost
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.010523713 = queryNorm
             0.7899883 = fieldWeight in 1678, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.09375 = fieldNorm(doc=1678)
       0.24 = coord(6/25)
   

4. Seco de Herrera, A.G.; Schaer, R.; Müller, H.: Shangri-La : a medical case-based retrieval tool (2017) 0.16

   0.16047885 = sum of:
     0.16047885 = product of:
       0.5731387 = sum of:
         0.01701355 = weight(abstract_txt:articles in 4924) [ClassicSimilarity], result of:
           0.01701355 = score(doc=4924,freq=1.0), product of:
             0.05695139 = queryWeight, product of:
               1.132204 = boost
               4.7798095 = idf(docFreq=1013, maxDocs=44421)
               0.010523713 = queryNorm
             0.2987381 = fieldWeight in 4924, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.7798095 = idf(docFreq=1013, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
         0.010802451 = weight(abstract_txt:information in 4924) [ClassicSimilarity], result of:
           0.010802451 = score(doc=4924,freq=6.0), product of:
             0.02917083 = queryWeight, product of:
               1.1459402 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.010523713 = queryNorm
             0.37031686 = fieldWeight in 4924, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
         0.0218071 = weight(abstract_txt:text in 4924) [ClassicSimilarity], result of:
           0.0218071 = score(doc=4924,freq=2.0), product of:
             0.061055776 = queryWeight, product of:
               1.4357591 = boost
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.010523713 = queryNorm
             0.3571669 = fieldWeight in 4924, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               4.040882 = idf(docFreq=2122, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
         0.07138637 = weight(abstract_txt:visual in 4924) [ClassicSimilarity], result of:
           0.07138637 = score(doc=4924,freq=3.0), product of:
             0.11759113 = queryWeight, product of:
               1.9925327 = boost
               5.6078978 = idf(docFreq=442, maxDocs=44421)
               0.010523713 = queryNorm
             0.6070727 = fieldWeight in 4924, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               5.6078978 = idf(docFreq=442, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
         0.10657442 = weight(abstract_txt:modality in 4924) [ClassicSimilarity], result of:
           0.10657442 = score(doc=4924,freq=1.0), product of:
             0.19352765 = queryWeight, product of:
               2.0871038 = boost
               8.811096 = idf(docFreq=17, maxDocs=44421)
               0.010523713 = queryNorm
             0.5506935 = fieldWeight in 4924, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.811096 = idf(docFreq=17, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
         0.029170183 = weight(abstract_txt:features in 4924) [ClassicSimilarity], result of:
           0.029170183 = score(doc=4924,freq=1.0), product of:
             0.10278833 = queryWeight, product of:
               2.1510944 = boost
               4.5406218 = idf(docFreq=1287, maxDocs=44421)
               0.010523713 = queryNorm
             0.28378886 = fieldWeight in 4924, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.5406218 = idf(docFreq=1287, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
         0.3163846 = weight(abstract_txt:multimodal in 4924) [ClassicSimilarity], result of:
           0.3163846 = score(doc=4924,freq=3.0), product of:
             0.34921068 = queryWeight, product of:
               3.9648917 = boost
               8.369263 = idf(docFreq=27, maxDocs=44421)
               0.010523713 = queryNorm
             0.90599924 = fieldWeight in 4924, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               8.369263 = idf(docFreq=27, maxDocs=44421)
               0.0625 = fieldNorm(doc=4924)
       0.28 = coord(7/25)
   

5. Ahmad, N.: Newspaper indexing : an international overview (1991) 0.15

   0.1518633 = sum of:
     0.1518633 = product of:
       0.7593165 = sum of:
         0.023280017 = weight(abstract_txt:identify in 3632) [ClassicSimilarity], result of:
           0.023280017 = score(doc=3632,freq=1.0), product of:
             0.060490876 = queryWeight, product of:
               1.1668566 = boost
               4.9261017 = idf(docFreq=875, maxDocs=44421)
               0.010523713 = queryNorm
             0.3848517 = fieldWeight in 3632, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.9261017 = idf(docFreq=875, maxDocs=44421)
               0.078125 = fieldNorm(doc=3632)
         0.024516528 = weight(abstract_txt:analysis in 3632) [ClassicSimilarity], result of:
           0.024516528 = score(doc=3632,freq=3.0), product of:
             0.04969702 = queryWeight, product of:
               1.2953387 = boost
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.010523713 = queryNorm
             0.4933199 = fieldWeight in 3632, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               3.6456752 = idf(docFreq=3151, maxDocs=44421)
               0.078125 = fieldNorm(doc=3632)
         0.039516374 = weight(abstract_txt:multiple in 3632) [ClassicSimilarity], result of:
           0.039516374 = score(doc=3632,freq=1.0), product of:
             0.09853326 = queryWeight, product of:
               1.8239361 = boost
               5.1333895 = idf(docFreq=711, maxDocs=44421)
               0.010523713 = queryNorm
             0.40104604 = fieldWeight in 3632, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.1333895 = idf(docFreq=711, maxDocs=44421)
               0.078125 = fieldNorm(doc=3632)
         0.11697597 = weight(abstract_txt:stories in 3632) [ClassicSimilarity], result of:
           0.11697597 = score(doc=3632,freq=1.0), product of:
             0.2031402 = queryWeight, product of:
               2.6188831 = boost
               7.370734 = idf(docFreq=75, maxDocs=44421)
               0.010523713 = queryNorm
             0.5758386 = fieldWeight in 3632, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               7.370734 = idf(docFreq=75, maxDocs=44421)
               0.078125 = fieldNorm(doc=3632)
         0.5550276 = weight(abstract_txt:news in 3632) [ClassicSimilarity], result of:
           0.5550276 = score(doc=3632,freq=6.0), product of:
             0.48675966 = queryWeight, product of:
               7.7626715 = boost
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.010523713 = queryNorm
             1.1402498 = fieldWeight in 3632, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               5.9584646 = idf(docFreq=311, maxDocs=44421)
               0.078125 = fieldNorm(doc=3632)
       0.2 = coord(5/25)