{"analysisVersion":"1.1.0","analyzedAt":"2026-08-10","corpus":{"name":"MovieSum","creators":["Rohit Saxena","Frank Keller"],"source":"https://huggingface.co/datasets/rohitsaxena/MovieSum","paper":"https://aclanthology.org/2024.findings-acl.239/","license":"CC BY-NC 4.0","licenseUrl":"https://creativecommons.org/licenses/by-nc/4.0/","adaptationNotice":"Aggregate analysis adapted from MovieSum; no screenplay text, summaries, identifiers, or title-level measurements are redistributed.","inputSha256":"5992b076833b40a88ae96f3c9740dc615bff94b76d27f32ac2a6ad72213215f1","records":2200,"includedRecords":2077,"excludedRecords":123,"exclusionCounts":{"too_few_scenes":107,"too_few_speaking_characters":15,"too_few_dialogue_blocks":17,"too_few_narrative_words":1}},"method":{"unitOfAnalysis":"One screenplay receives equal weight in every corpus summary.","progressDefinition":"Scenes are assigned by the midpoint of their action-plus-dialogue word count after each screenplay is normalized to 100%.","actionDefinition":"Words tagged scene_description divided by scene_description plus dialogue words.","characterDefinition":"A normalized character cue followed by at least one dialogue block.","longestSceneDefinition":"The share of a screenplay's action-plus-dialogue words contained in its longest 10% of scenes, rounding the scene count up.","dialogueFreeSceneDefinition":"The share of parsed scenes containing no tagged dialogue words.","thresholds":{"minimumScenes":20,"minimumNarrativeWords":5000,"minimumSpeakingCharacters":3,"minimumDialogueBlocks":20},"bootstrap":{"statistic":"median","interval":"percentile 95%","replicates":2000,"seed":20260810}},"overview":{"narrativeWords":{"p10":15871.6,"p25":18380,"median":21579,"p75":25179,"p90":29019.4},"tokenizedNarrativeWords":{"p10":15476.4,"p25":17908,"median":20759,"p75":23715,"p90":27087.2},"sceneCount":{"p10":68,"p25":97,"median":130,"p75":168,"p90":211},"medianSceneWords":{"p10":52.5,"p25":70,"median":94,"p75":132,"p90":189},"longestSceneDecileShare":{"p10":0.317,"p25":0.3455,"median":0.3792,"p75":0.4199,"p90":0.4615},"dialogueFreeSceneShare":{"p10":0.1329,"p25":0.2027,"median":0.2945,"p75":0.3852,"p90":0.4697},"speakingCharacterCount":{"p10":26,"p25":36,"median":50,"p75":72,"p90":110},"actionShare":{"p10":0.3957,"p25":0.4859,"median":0.579,"p75":0.6751,"p90":0.7398},"topThreeDialogueShare":{"p10":0.3979,"p25":0.4798,"median":0.5718,"p75":0.6603,"p90":0.7354},"headingCoverage":{"p10":0.9863,"p25":0.9913,"median":0.9947,"p75":1,"p90":1},"summaryWords":{"p10":410.6,"p25":538,"median":656,"p75":714,"p90":801.4},"compressionRatio":{"p10":0.019,"p25":0.025,"median":0.0302,"p75":0.0366,"p90":0.0443},"aggregateCompressionRatio":0.0298,"novelNgrams":{"unigram":{"p10":0.242,"p25":0.2718,"median":0.3056,"p75":0.3426,"p90":0.3784},"bigram":{"p10":0.6727,"p25":0.6993,"median":0.726,"p75":0.7557,"p90":0.7824},"trigram":{"p10":0.9236,"p25":0.9378,"median":0.9511,"p75":0.9627,"p90":0.9717}},"scriptLengthLogNormalFit":{"mu":9.9276,"sigma":0.2391,"rawSkewness":0.7502,"logSkewness":-0.5862,"kolmogorovSmirnovD":0.0394},"summaryLengthLogNormalFit":{"mu":6.3787,"sigma":0.4305,"rawSkewness":0.0553,"logSkewness":-3.4142,"kolmogorovSmirnovD":0.178}},"progress":[{"decile":1,"range":"0–10%","actionShare":{"p10":0.4186,"p25":0.5257,"median":0.6382,"p75":0.743,"p90":0.8262,"confidence95":{"low":0.6318,"high":0.6486}},"scenes":{"p10":5,"p25":8,"median":13,"p75":17,"p90":23,"confidence95":{"low":12,"high":13}},"speakingCastIntroduced":{"p10":0.1247,"p25":0.1613,"median":0.2174,"p75":0.2807,"p90":0.3571,"confidence95":{"low":0.2121,"high":0.2211}}},{"decile":2,"range":"10–20%","actionShare":{"p10":0.3419,"p25":0.439,"median":0.5573,"p75":0.6598,"p90":0.755,"confidence95":{"low":0.5501,"high":0.566}},"scenes":{"p10":5,"p25":7,"median":11,"p75":16,"p90":21,"confidence95":{"low":11,"high":11}},"speakingCastIntroduced":{"p10":0.2338,"p25":0.2885,"median":0.3571,"p75":0.4444,"p90":0.5202,"confidence95":{"low":0.3511,"high":0.3636}}},{"decile":3,"range":"20–30%","actionShare":{"p10":0.3339,"p25":0.4471,"median":0.5514,"p75":0.6657,"p90":0.7656,"confidence95":{"low":0.5434,"high":0.5607}},"scenes":{"p10":5,"p25":8,"median":11,"p75":16,"p90":22,"confidence95":{"low":11,"high":12}},"speakingCastIntroduced":{"p10":0.3333,"p25":0.3881,"median":0.4651,"p75":0.5556,"p90":0.6414,"confidence95":{"low":0.4603,"high":0.4727}}},{"decile":4,"range":"30–40%","actionShare":{"p10":0.3418,"p25":0.4361,"median":0.5474,"p75":0.6584,"p90":0.7612,"confidence95":{"low":0.5389,"high":0.5569}},"scenes":{"p10":5,"p25":8,"median":12,"p75":17,"p90":23,"confidence95":{"low":11,"high":12}},"speakingCastIntroduced":{"p10":0.4245,"p25":0.4848,"median":0.56,"p75":0.6458,"p90":0.7253,"confidence95":{"low":0.5541,"high":0.5667}}},{"decile":5,"range":"40–50%","actionShare":{"p10":0.3345,"p25":0.4314,"median":0.5447,"p75":0.6535,"p90":0.7569,"confidence95":{"low":0.5351,"high":0.5535}},"scenes":{"p10":5,"p25":8,"median":12,"p75":17,"p90":22.4,"confidence95":{"low":11,"high":12}},"speakingCastIntroduced":{"p10":0.5152,"p25":0.5726,"median":0.65,"p75":0.7308,"p90":0.8046,"confidence95":{"low":0.6429,"high":0.6552}}},{"decile":6,"range":"50–60%","actionShare":{"p10":0.3396,"p25":0.444,"median":0.5446,"p75":0.6617,"p90":0.7669,"confidence95":{"low":0.5375,"high":0.5529}},"scenes":{"p10":5,"p25":8,"median":12,"p75":17,"p90":23,"confidence95":{"low":12,"high":12}},"speakingCastIntroduced":{"p10":0.6026,"p25":0.6591,"median":0.7339,"p75":0.8033,"p90":0.8681,"confidence95":{"low":0.7292,"high":0.7407}}},{"decile":7,"range":"60–70%","actionShare":{"p10":0.3411,"p25":0.4455,"median":0.5572,"p75":0.6734,"p90":0.7703,"confidence95":{"low":0.5506,"high":0.5654}},"scenes":{"p10":5,"p25":8,"median":12,"p75":18,"p90":24,"confidence95":{"low":12,"high":13}},"speakingCastIntroduced":{"p10":0.68,"p25":0.7407,"median":0.8056,"p75":0.8661,"p90":0.92,"confidence95":{"low":0.8,"high":0.8107}}},{"decile":8,"range":"70–80%","actionShare":{"p10":0.3381,"p25":0.4449,"median":0.5629,"p75":0.6845,"p90":0.7966,"confidence95":{"low":0.5522,"high":0.5755}},"scenes":{"p10":5,"p25":9,"median":13,"p75":18,"p90":25,"confidence95":{"low":12,"high":13}},"speakingCastIntroduced":{"p10":0.7725,"p25":0.8246,"median":0.8772,"p75":0.925,"p90":0.963,"confidence95":{"low":0.8718,"high":0.881}}},{"decile":9,"range":"80–90%","actionShare":{"p10":0.3599,"p25":0.4735,"median":0.5987,"p75":0.7327,"p90":0.8291,"confidence95":{"low":0.5879,"high":0.6102}},"scenes":{"p10":5,"p25":9,"median":14,"p75":20,"p90":27,"confidence95":{"low":13,"high":14}},"speakingCastIntroduced":{"p10":0.8684,"p25":0.9091,"median":0.9444,"p75":0.9737,"p90":1,"confidence95":{"low":0.9412,"high":0.9467}}},{"decile":10,"range":"90–100%","actionShare":{"p10":0.4194,"p25":0.5402,"median":0.6608,"p75":0.7848,"p90":0.8655,"confidence95":{"low":0.6481,"high":0.6696}},"scenes":{"p10":5,"p25":8,"median":14,"p75":20,"p90":28,"confidence95":{"low":13,"high":14}},"speakingCastIntroduced":{"p10":1,"p25":1,"median":1,"p75":1,"p90":1,"confidence95":{"low":1,"high":1}}}],"castDialogueBins":[{"label":"3–19","scripts":73,"speakingCharacters":{"p10":9.2,"p25":13,"median":15,"p75":17,"p90":19},"topThreeDialogueShare":{"p10":0.5947,"p25":0.6555,"median":0.7159,"p75":0.8308,"p90":0.9197}},{"label":"20–29","scripts":244,"speakingCharacters":{"p10":21,"p25":23,"median":26,"p75":27,"p90":29},"topThreeDialogueShare":{"p10":0.5107,"p25":0.5771,"median":0.6511,"p75":0.7365,"p90":0.7982}},{"label":"30–39","scripts":354,"speakingCharacters":{"p10":31,"p25":33,"median":35,"p75":37,"p90":38.7},"topThreeDialogueShare":{"p10":0.482,"p25":0.5346,"median":0.625,"p75":0.6986,"p90":0.7554}},{"label":"40–59","scripts":648,"speakingCharacters":{"p10":41,"p25":44.75,"median":49,"p75":54,"p90":57},"topThreeDialogueShare":{"p10":0.4277,"p25":0.5023,"median":0.582,"p75":0.6579,"p90":0.7178}},{"label":"60–79","scripts":350,"speakingCharacters":{"p10":61,"p25":63,"median":69,"p75":73,"p90":77},"topThreeDialogueShare":{"p10":0.3988,"p25":0.4567,"median":0.5236,"p75":0.6016,"p90":0.6759}},{"label":"80–119","scripts":231,"speakingCharacters":{"p10":81,"p25":86,"median":95,"p75":104,"p90":113},"topThreeDialogueShare":{"p10":0.3543,"p25":0.4099,"median":0.4927,"p75":0.5664,"p90":0.6284}},{"label":"120+","scripts":177,"speakingCharacters":{"p10":125,"p25":136,"median":164,"p75":235,"p90":312.4},"topThreeDialogueShare":{"p10":0.2671,"p25":0.3427,"median":0.4135,"p75":0.4914,"p90":0.5769}}],"relationships":{"narrativeWordsVsSceneCountSpearman":0.2549,"castSizeVsTopThreeDialogueShareSpearman":-0.5227,"scriptLengthVsSummaryLengthPearson":0.1258,"scriptLengthVsSummaryLengthSpearman":0.1643}}