Document (#43498)

Author

Tavakoli, L.
Zamani, H.
Scholer, F.
Croft, W.B.
Sanderson, M.

Title

Analyzing clarification in asynchronous information-seeking conversations

Source

Journal of the Association for Information Science and Technology. 73(2022) no.3, S.449-471

Year

2022

Abstract

This research analyzes human-generated clarification questions to provide insights into how they are used to disambiguate and provide a better understanding of information needs. A set of clarification questions is extracted from posts on the Stack Exchange platform. Novel taxonomy is defined for the annotation of the questions and their responses. We investigate the clarification questions in terms of whether they add any information to the post (the initial question posted by the asker) and the accepted answer, which is the answer chosen by the asker. After identifying, which clarification questions are more useful, we investigated the characteristics of these questions in terms of their types and patterns. Non-useful clarification questions are identified, and their patterns are compared with useful clarifications. Our analysis indicates that the most useful clarification questions have similar patterns, regardless of topic. This research contributes to an understanding of clarification in conversations and can provide insight for clarification dialogues in conversational search scenarios and for the possible system generation of clarification requests in information-seeking conversations.

Content

Vgl.: https://asistdl.onlinelibrary.wiley.com/doi/10.1002/asi.24562.

Similar documents (author)

1. Sanderson, M.: ¬The Reuters test collection (1996) 0.96

   0.95973015 = sum of:
     0.95973015 = product of:
       2.8791904 = sum of:
         2.8791904 = weight(author_txt:sanderson in 40) [ClassicSimilarity], result of:
           2.8791904 = score(doc=40,freq=1.0), product of:
             0.5377912 = queryWeight, product of:
               1.0656972 = boost
               8.565973 = idf(docFreq=22, maxDocs=44421)
               0.058911916 = queryNorm
             5.353733 = fieldWeight in 40, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.565973 = idf(docFreq=22, maxDocs=44421)
               0.625 = fieldNorm(doc=40)
       0.33333334 = coord(1/3)
   

2. Sanderson, M.: Revisiting h measured on UK LIS and IR academics (2008) 0.96

   0.95973015 = sum of:
     0.95973015 = product of:
       2.8791904 = sum of:
         2.8791904 = weight(author_txt:sanderson in 2867) [ClassicSimilarity], result of:
           2.8791904 = score(doc=2867,freq=1.0), product of:
             0.5377912 = queryWeight, product of:
               1.0656972 = boost
               8.565973 = idf(docFreq=22, maxDocs=44421)
               0.058911916 = queryNorm
             5.353733 = fieldWeight in 2867, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.565973 = idf(docFreq=22, maxDocs=44421)
               0.625 = fieldNorm(doc=2867)
       0.33333334 = coord(1/3)
   

3. Scholer, F.; Williams, H.E.; Turpin, A.: Query association surrogates for Web search (2004) 0.85

   0.8506021 = sum of:
     0.8506021 = product of:
       2.5518062 = sum of:
         2.5518062 = weight(author_txt:scholer in 3236) [ClassicSimilarity], result of:
           2.5518062 = score(doc=3236,freq=1.0), product of:
             0.69753236 = queryWeight, product of:
               1.2136939 = boost
               9.755557 = idf(docFreq=6, maxDocs=44421)
               0.058911916 = queryNorm
             3.6583338 = fieldWeight in 3236, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.755557 = idf(docFreq=6, maxDocs=44421)
               0.375 = fieldNorm(doc=3236)
       0.33333334 = coord(1/3)
   

4. Bando, L.L.; Scholer, F.; Turpin, A.: Query-biased summary generation assisted by query expansion : temporality (2015) 0.85

   0.8506021 = sum of:
     0.8506021 = product of:
       2.5518062 = sum of:
         2.5518062 = weight(author_txt:scholer in 2820) [ClassicSimilarity], result of:
           2.5518062 = score(doc=2820,freq=1.0), product of:
             0.69753236 = queryWeight, product of:
               1.2136939 = boost
               9.755557 = idf(docFreq=6, maxDocs=44421)
               0.058911916 = queryNorm
             3.6583338 = fieldWeight in 2820, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               9.755557 = idf(docFreq=6, maxDocs=44421)
               0.375 = fieldNorm(doc=2820)
       0.33333334 = coord(1/3)
   

5. Croft, W.B.: Approaches to intelligent information retrieval (1987) 0.79

   0.7929535 = sum of:
     0.7929535 = product of:
       2.3788605 = sum of:
         2.3788605 = weight(author_txt:croft in 1093) [ClassicSimilarity], result of:
           2.3788605 = score(doc=1093,freq=1.0), product of:
             0.47352841 = queryWeight, product of:
               8.037906 = idf(docFreq=38, maxDocs=44421)
               0.058911916 = queryNorm
             5.023691 = fieldWeight in 1093, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.037906 = idf(docFreq=38, maxDocs=44421)
               0.625 = fieldNorm(doc=1093)
       0.33333334 = coord(1/3)
   

Similar documents (content)

1. Raskutti, B.; Zukerman, I.: Generating queries and replies during information-seeking interactions (1997) 0.22

   0.22370607 = sum of:
     0.22370607 = product of:
       0.93210864 = sum of:
         0.01065454 = weight(abstract_txt:they in 2662) [ClassicSimilarity], result of:
           0.01065454 = score(doc=2662,freq=1.0), product of:
             0.036388867 = queryWeight, product of:
               1.0955821 = boost
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.008862321 = queryNorm
             0.2927967 = fieldWeight in 2662, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.7477977 = idf(docFreq=2845, maxDocs=44421)
               0.078125 = fieldNorm(doc=2662)
         0.06795894 = weight(abstract_txt:dialogues in 2662) [ClassicSimilarity], result of:
           0.06795894 = score(doc=2662,freq=1.0), product of:
             0.09933443 = queryWeight, product of:
               1.2799575 = boost
               8.757029 = idf(docFreq=18, maxDocs=44421)
               0.008862321 = queryNorm
             0.6841428 = fieldWeight in 2662, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.757029 = idf(docFreq=18, maxDocs=44421)
               0.078125 = fieldNorm(doc=2662)
         0.01145829 = weight(abstract_txt:information in 2662) [ClassicSimilarity], result of:
           0.01145829 = score(doc=2662,freq=4.0), product of:
             0.030316701 = queryWeight, product of:
               1.4142189 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.008862321 = queryNorm
             0.37795305 = fieldWeight in 2662, product of:
               2.0 = tf(freq=4.0), with freq of:
                 4.0 = termFreq=4.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.078125 = fieldNorm(doc=2662)
         0.026576461 = weight(abstract_txt:seeking in 2662) [ClassicSimilarity], result of:
           0.026576461 = score(doc=2662,freq=1.0), product of:
             0.06692836 = queryWeight, product of:
               1.4858185 = boost
               5.082729 = idf(docFreq=748, maxDocs=44421)
               0.008862321 = queryNorm
             0.3970882 = fieldWeight in 2662, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.082729 = idf(docFreq=748, maxDocs=44421)
               0.078125 = fieldNorm(doc=2662)
         0.04181201 = weight(abstract_txt:answer in 2662) [ClassicSimilarity], result of:
           0.04181201 = score(doc=2662,freq=1.0), product of:
             0.090534225 = queryWeight, product of:
               1.7280928 = boost
               5.9115076 = idf(docFreq=326, maxDocs=44421)
               0.008862321 = queryNorm
             0.46183652 = fieldWeight in 2662, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               5.9115076 = idf(docFreq=326, maxDocs=44421)
               0.078125 = fieldNorm(doc=2662)
         0.7736484 = weight(abstract_txt:clarification in 2662) [ClassicSimilarity], result of:
           0.7736484 = score(doc=2662,freq=2.0), product of:
             0.859583 = queryWeight, product of:
               11.90665 = boost
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.008862321 = queryNorm
             0.9000275 = fieldWeight in 2662, product of:
               1.4142135 = tf(freq=2.0), with freq of:
                 2.0 = termFreq=2.0
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.078125 = fieldNorm(doc=2662)
       0.24 = coord(6/25)
   

2. Sowa, J.F.: Top-level ontological categories (1995) 0.15

   0.15017633 = sum of:
     0.15017633 = product of:
       0.9386021 = sum of:
         0.0133151105 = weight(abstract_txt:their in 4811) [ClassicSimilarity], result of:
           0.0133151105 = score(doc=4811,freq=1.0), product of:
             0.038617752 = queryWeight, product of:
               1.3822919 = boost
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.008862321 = queryNorm
             0.3447925 = fieldWeight in 4811, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.109375 = fieldNorm(doc=4811)
         0.027487459 = weight(abstract_txt:provide in 4811) [ClassicSimilarity], result of:
           0.027487459 = score(doc=4811,freq=1.0), product of:
             0.062610455 = queryWeight, product of:
               1.7600691 = boost
               4.013929 = idf(docFreq=2180, maxDocs=44421)
               0.008862321 = queryNorm
             0.43902346 = fieldWeight in 4811, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.013929 = idf(docFreq=2180, maxDocs=44421)
               0.109375 = fieldNorm(doc=4811)
         0.1319267 = weight(abstract_txt:questions in 4811) [ClassicSimilarity], result of:
           0.1319267 = score(doc=4811,freq=1.0), product of:
             0.24704072 = queryWeight, product of:
               5.7091956 = boost
               4.8825436 = idf(docFreq=914, maxDocs=44421)
               0.008862321 = queryNorm
             0.5340282 = fieldWeight in 4811, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.8825436 = idf(docFreq=914, maxDocs=44421)
               0.109375 = fieldNorm(doc=4811)
         0.76587284 = weight(abstract_txt:clarification in 4811) [ClassicSimilarity], result of:
           0.76587284 = score(doc=4811,freq=1.0), product of:
             0.859583 = queryWeight, product of:
               11.90665 = boost
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.008862321 = queryNorm
             0.8909818 = fieldWeight in 4811, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.109375 = fieldNorm(doc=4811)
       0.16 = coord(4/25)
   

3. Krasakis, A.M.; Yates, A.; Kanoulas, E.: Corpus-informed Retrieval Augmented Generation of Clarifying Questions (2024) 0.14

   0.13936694 = sum of:
     0.13936694 = product of:
       0.6968347 = sum of:
         0.116427526 = weight(abstract_txt:clarifications in 2369) [ClassicSimilarity], result of:
           0.116427526 = score(doc=2369,freq=3.0), product of:
             0.114429705 = queryWeight, product of:
               1.3737732 = boost
               9.398883 = idf(docFreq=9, maxDocs=44421)
               0.008862321 = queryNorm
             1.0174589 = fieldWeight in 2369, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               9.398883 = idf(docFreq=9, maxDocs=44421)
               0.0625 = fieldNorm(doc=2369)
         0.0076086344 = weight(abstract_txt:their in 2369) [ClassicSimilarity], result of:
           0.0076086344 = score(doc=2369,freq=1.0), product of:
             0.038617752 = queryWeight, product of:
               1.3822919 = boost
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.008862321 = queryNorm
             0.19702427 = fieldWeight in 2369, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.0625 = fieldNorm(doc=2369)
         0.004583316 = weight(abstract_txt:information in 2369) [ClassicSimilarity], result of:
           0.004583316 = score(doc=2369,freq=1.0), product of:
             0.030316701 = queryWeight, product of:
               1.4142189 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.008862321 = queryNorm
             0.15118122 = fieldWeight in 2369, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.0625 = fieldNorm(doc=2369)
         0.13057359 = weight(abstract_txt:questions in 2369) [ClassicSimilarity], result of:
           0.13057359 = score(doc=2369,freq=3.0), product of:
             0.24704072 = queryWeight, product of:
               5.7091956 = boost
               4.8825436 = idf(docFreq=914, maxDocs=44421)
               0.008862321 = queryNorm
             0.52855086 = fieldWeight in 2369, product of:
               1.7320508 = tf(freq=3.0), with freq of:
                 3.0 = termFreq=3.0
               4.8825436 = idf(docFreq=914, maxDocs=44421)
               0.0625 = fieldNorm(doc=2369)
         0.4376416 = weight(abstract_txt:clarification in 2369) [ClassicSimilarity], result of:
           0.4376416 = score(doc=2369,freq=1.0), product of:
             0.859583 = queryWeight, product of:
               11.90665 = boost
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.008862321 = queryNorm
             0.50913244 = fieldWeight in 2369, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.0625 = fieldNorm(doc=2369)
       0.2 = coord(5/25)
   

4. Solomon, P.: Conversation in information seeking contexts : a test of an analytical framework (1997) 0.13

   0.13315266 = sum of:
     0.13315266 = product of:
       0.5548028 = sum of:
         0.057869934 = weight(abstract_txt:conversational in 1503) [ClassicSimilarity], result of:
           0.057869934 = score(doc=1503,freq=1.0), product of:
             0.089242294 = queryWeight, product of:
               1.2131962 = boost
               8.30027 = idf(docFreq=29, maxDocs=44421)
               0.008862321 = queryNorm
             0.6484586 = fieldWeight in 1503, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.30027 = idf(docFreq=29, maxDocs=44421)
               0.078125 = fieldNorm(doc=1503)
         0.06795894 = weight(abstract_txt:dialogues in 1503) [ClassicSimilarity], result of:
           0.06795894 = score(doc=1503,freq=1.0), product of:
             0.09933443 = queryWeight, product of:
               1.2799575 = boost
               8.757029 = idf(docFreq=18, maxDocs=44421)
               0.008862321 = queryNorm
             0.6841428 = fieldWeight in 1503, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.757029 = idf(docFreq=18, maxDocs=44421)
               0.078125 = fieldNorm(doc=1503)
         0.009510794 = weight(abstract_txt:their in 1503) [ClassicSimilarity], result of:
           0.009510794 = score(doc=1503,freq=1.0), product of:
             0.038617752 = queryWeight, product of:
               1.3822919 = boost
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.008862321 = queryNorm
             0.24628034 = fieldWeight in 1503, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.078125 = fieldNorm(doc=1503)
         0.014033482 = weight(abstract_txt:information in 1503) [ClassicSimilarity], result of:
           0.014033482 = score(doc=1503,freq=6.0), product of:
             0.030316701 = queryWeight, product of:
               1.4142189 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.008862321 = queryNorm
             0.46289608 = fieldWeight in 1503, product of:
               2.4494898 = tf(freq=6.0), with freq of:
                 6.0 = termFreq=6.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.078125 = fieldNorm(doc=1503)
         0.059426773 = weight(abstract_txt:seeking in 1503) [ClassicSimilarity], result of:
           0.059426773 = score(doc=1503,freq=5.0), product of:
             0.06692836 = queryWeight, product of:
               1.4858185 = boost
               5.082729 = idf(docFreq=748, maxDocs=44421)
               0.008862321 = queryNorm
             0.8879162 = fieldWeight in 1503, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               5.082729 = idf(docFreq=748, maxDocs=44421)
               0.078125 = fieldNorm(doc=1503)
         0.34600288 = weight(abstract_txt:conversations in 1503) [ClassicSimilarity], result of:
           0.34600288 = score(doc=1503,freq=5.0), product of:
             0.24795468 = queryWeight, product of:
               3.5026152 = boost
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.008862321 = queryNorm
             1.395428 = fieldWeight in 1503, product of:
               2.236068 = tf(freq=5.0), with freq of:
                 5.0 = termFreq=5.0
               7.9878955 = idf(docFreq=40, maxDocs=44421)
               0.078125 = fieldNorm(doc=1503)
       0.24 = coord(6/25)
   

5. Tunkelang, D.: Dynamic category sets : an approach for faceted search (2006) 0.13

   0.12826602 = sum of:
     0.12826602 = product of:
       0.64133006 = sum of:
         0.013382801 = weight(abstract_txt:terms in 69) [ClassicSimilarity], result of:
           0.013382801 = score(doc=69,freq=1.0), product of:
             0.042362027 = queryWeight, product of:
               1.1820859 = boost
               4.043712 = idf(docFreq=2116, maxDocs=44421)
               0.008862321 = queryNorm
             0.31591502 = fieldWeight in 69, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               4.043712 = idf(docFreq=2116, maxDocs=44421)
               0.078125 = fieldNorm(doc=69)
         0.06565538 = weight(abstract_txt:disambiguate in 69) [ClassicSimilarity], result of:
           0.06565538 = score(doc=69,freq=1.0), product of:
             0.09707684 = queryWeight, product of:
               1.265329 = boost
               8.656945 = idf(docFreq=20, maxDocs=44421)
               0.008862321 = queryNorm
             0.67632383 = fieldWeight in 69, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.656945 = idf(docFreq=20, maxDocs=44421)
               0.078125 = fieldNorm(doc=69)
         0.009510794 = weight(abstract_txt:their in 69) [ClassicSimilarity], result of:
           0.009510794 = score(doc=69,freq=1.0), product of:
             0.038617752 = queryWeight, product of:
               1.3822919 = boost
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.008862321 = queryNorm
             0.24628034 = fieldWeight in 69, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               3.1523883 = idf(docFreq=5161, maxDocs=44421)
               0.078125 = fieldNorm(doc=69)
         0.005729145 = weight(abstract_txt:information in 69) [ClassicSimilarity], result of:
           0.005729145 = score(doc=69,freq=1.0), product of:
             0.030316701 = queryWeight, product of:
               1.4142189 = boost
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.008862321 = queryNorm
             0.18897653 = fieldWeight in 69, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               2.4188995 = idf(docFreq=10748, maxDocs=44421)
               0.078125 = fieldNorm(doc=69)
         0.54705197 = weight(abstract_txt:clarification in 69) [ClassicSimilarity], result of:
           0.54705197 = score(doc=69,freq=1.0), product of:
             0.859583 = queryWeight, product of:
               11.90665 = boost
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.008862321 = queryNorm
             0.63641554 = fieldWeight in 69, product of:
               1.0 = tf(freq=1.0), with freq of:
                 1.0 = termFreq=1.0
               8.146119 = idf(docFreq=34, maxDocs=44421)
               0.078125 = fieldNorm(doc=69)
       0.2 = coord(5/25)