Upgrade to Pro — share decks privately, control downloads, hide ads and more …

ヒューマンコンピュテーション入門 / Introduction to Human Comput...

ヒューマンコンピュテーション入門 / Introduction to Human Computation

Transcript

  1. /20 ώϡʔϚϯίϯϐϡςʔγϣϯͷྫ 7JT8J[ࢹ֮ো͕͍ऀͷ࣭໰Ԡ౴γεςϜʹਓؒΛ૊ΈࠐΉ  -tap to take a photo. 

    -tap to begin recording your question and again to stop.        side,     User     ? Database - Local Client Remote Services and Worker Interface 4UFQϢʔβ͕࣭໰Λ౤ߘ 4UFQγεςϜ಺෦ͷਓ͕ؒճ౴ ίʔϯͷ؈͸ͲΕʁ Ұ൪ӈͷ؈Ͱ͢ 3 J. Bigham et al.: VizWiz: Nearly real-time answers to visual questions, In UIST, 2010.
  2. /20 ΞΫηε੍ޚʹΑΔಈػ͚ͮ w ਖ਼ղະ஌ʢೝࣝର৅ʣͱਖ਼ղط஌ͷจࣈྻͷ྆ํʹճ౴͢ΔΑ͏ࢦࣔ͢Δ w ਖ਼ղط஌ͷํΛ࢖ͬͯਓؒʢʹਖ਼͘͠౴͑ΒΕΔਓʣ͔Ͳ͏͔൑ఆ͢Δ w ͲͪΒ͕ਖ਼ղط஌ͳͷ͔͸ఏࣔ͠ͳ͍ͨΊࣗ෼͕ਓؒͩͱূ໌͍ͨ͠ਓ͸ ྆ํʹਅ໘໨ʹऔΓ૊·ͳ͍ͱ͍͚ͳ͍ w

    ਓ͚͕ؒͩ൑ఆͰ͖ΔΑ͏ʹจࣈྻΛগ͠࿪·ͤΔ ਖ਼ղط஌ͷ໰୊ΛࠞͥΔ͜ͱͰෆਅ໘໨ͳਓΛআ֎͢Δ ਖ਼ղະ஌ ਖ਼ղط஌ ਖ਼౴ͩͱਓؒ
 ޡ౴ͩͱϘοτͱ൑ఆ͞ΕΔ 7 L. von Ahn et al.: reCAPTCHA: Human-based character recognition via web security measures, Science, 2008.
  3. /20 ۚમʹΑΔಈػ͚ͮ w ۚમใु͸ಈػ͚ͮͷ൚༻తͳखஈ w ΠϯλʔωοτΛ௨ͯ͡ෆಛఆଟ਺ͷਓʑʹ࡞ۀΛൃ஫͢Δ࢓૊Έ
 ʮΫϥ΢υιʔγϯάʯʹΑΓ͓ۚΛࢧ෷͍ࢀՃऀΛूΊΔ͜ͱ͕Ͱ͖Δ ⿞Ϋϥ΢υιʔγϯάͷྫɿ"NB[PO.FDIBOJDBM5VSL ϥϯαʔζ w

    7J[8J[͸Ϋϥ΢υιʔγϯάΛ༻͍ͯࢀՃऀΛ֬อ Ϋϥ΢υιʔγϯάɿෆಛఆଟ਺ͷਓʹใुΛ෷͍࡞ۀΛґཔ Ϋϥ΢υιʔγϯά ࡞ۀΛൃ஫ අ༻Λࢧ෷͏ ࡞ۀΛड஫ ใुΛ੥ٻ 12
  4. /20 ฒྻ໰߹ͤʹΑΔ඼࣭อূ w ճ౴͔Β֤ࣗͷ৴པੑΛਪఆ্ͨ͠Ͱ֤໰୊ͷਖ਼ղΛ༧ଌ͢Δ ⿞ੜెͷճ౴͚͔ͩΒࢼݧͷਖ਼ղΛ༧ଌ͢ΔΑ͏ͳ΋ͷ ճ౴͔Β֤ࣗͷ৴པੑΛ౷ܭతʹਪఆ͢Δ YES YES YES YES

    NO YES NO YES YES YES YES NO ? ? ? ਖ਼ղ ਖ਼ղ 14 A. P. Dawid and A. M. Skene: Maximum likelihood estimation of observer error-rates using the EM algorithm, 
 Journal of the Royal Statistical Society. Series C (Applied Statistics), 1979.
  5. /20 ਪનʹΑΔ඼࣭อূ w શถՕॴʹ੺͍෩ધΛઃஔ w ࠷ॳʹશͯͷ੺͍෩ધΛݟ͚ͭͨνʔϜʹ৆͕ۚࢧ෷ΘΕΔίϯςετ w ༏উνʔϜ͸ʮ෩ધΛݟ͚ͭͦ͏ͳਓʯΛଞऀ͔ΒͷਪનͰൃݟ %"31"3FE#BMMPPO$IBMMFOHF੺͍෩ધΛ୳͢ίϯςετ contributed

    articles platform for viral collaboration that used recursive incentives to align the public’s interest with the goal of win- ning the Challenge. This approach was inspired by the work of Peter S. Dodds et al.5 that found that success in us- ing social networks to tackle widely distributed search problems depends on individual incentives. The work of Mason and Watts7 also informed the use of financial incentives to motivate crowdsourcing productivity. The MIT team’s winning strategy was to use the prize money as a finan- cial incentive structure rewarding not only the people who correctly located balloons but also those connecting the finder to the MIT team. Should the team win, they would allocate $4,000 in prize money to each balloon. They Figure 1. Locations in the DARPA Red Balloon Challenge. Figure 2. Example recursive incentive-structure process for the MIT team. 18 J. Tang et al.: Reflecting on the DARPA red balloon challenge, Communications of the ACM, 2011.