{"analysisVersion":"0.2.0","analyzedAt":"2026-08-21","corpus":{"name":"Movie Script Database — IMSDb tagged archive","creator":"Aveek Saha","sourceRepository":"https://github.com/Aveek-Saha/Movie-Script-Database","sourceArchive":"https://doi.org/10.5281/zenodo.14841817","archiveLicense":"CC BY 4.0","archiveLicenseUrl":"https://creativecommons.org/licenses/by/4.0/","upstreamSoftwareLicense":"MIT","archiveMd5":"6b1977bafb6036b0847f06da4423a560","inputSha256":"7450edc32eab5631655901c0b9b058ed8e5b6e5f1cefdd36a568173f5aac3b3a","textFiles":1088,"includedRecords":994,"excludedRecords":94,"exclusionCounts":{"too_few_dialogue_turns":16,"too_few_speaking_characters":13,"too_few_dialogue_scenes":92,"too_few_speaker_changes":69},"adaptationNotice":"Aggregate structural analysis of the tagged archive. No screenplay text, character names, titles, identifiers, or title-level measurements are redistributed."},"method":{"unitOfAnalysis":"One eligible screenplay receives equal weight in every corpus summary.","dialogueTurnDefinition":"A parsed D: dialogue block attached to the most recent normalized C: character cue.","sceneDefinition":"A parsed S: scene heading starts a scene. Dialogue before the first S: contributes to whole-script dialogue measures but not scene measures.","characterNormalization":"Unicode NFKC + uppercase + whitespace collapse, then recognized delivery extensions are stripped repeatedly from the cue suffix until no recognized extension remains.","adjacentPairDefinition":"An unordered pair of different normalized speakers on consecutive dialogue turns inside the same parsed headed scene. Adjacency does not assert addressee or relationship semantics.","effectiveSpeakersDefinition":"Inverse Simpson concentration, 1 / sum(p_i^2), over each character's share of dialogue turns.","peripheralMeasures":{"oneTurnSpeakerShare":"Share of speaking characters with exactly one parsed dialogue turn.","fiveOrFewerTurnSpeakerShare":"Share of speaking characters with five or fewer parsed dialogue turns.","singleDialogueSceneSpeakerShare":"Share of speaking characters whose dialogue appears in exactly one headed dialogue-bearing scene."},"giniDefinition":"Gini coefficient over per-character dialogue-turn counts.","thresholds":{"minimumDialogueTurns":20,"minimumSpeakingCharacters":3,"minimumDialogueScenes":10,"minimumSpeakerChanges":20},"bootstrap":{"statistic":"median","interval":"percentile 95%","replicates":2000,"seed":20260821},"caveats":["The upstream parser is heuristic and can misclassify cues, dialogue, and scene headings, especially in OCR-derived scripts.","Character cues are normalized syntactically; aliases and renamed characters are not coreference-resolved.","Adjacent dialogue turns are a structural proxy for conversational topology, not proof of addressee or relationship semantics.","The IMSDb tagged archive is a convenience sample, not a representative sample of all produced or sold screenplays."]},"overview":{"dialogueTurns":{"p10":551.3,"p25":678,"median":812,"p75":966.75,"p90":1101.4,"confidence95":{"low":795,"high":830}},"dialogueWords":{"p10":5448.2,"p25":7075.5,"median":9243.5,"p75":12022.25,"p90":15141.8,"confidence95":{"low":8998,"high":9600.575}},"speakingCharacters":{"p10":25,"p25":34,"median":47,"p75":66,"p90":97,"confidence95":{"low":45,"high":48}},"medianTurnWords":{"p10":5.65,"p25":6,"median":7,"p75":9,"p90":11.35,"confidence95":{"low":7,"high":7}},"p90TurnWords":{"p10":18,"p25":20,"median":24,"p75":30,"p90":36,"confidence95":{"low":24,"high":25}},"medianTurnsPerSpeaker":{"p10":1,"p25":2,"median":3,"p75":4,"p90":6,"confidence95":{"low":2.5,"high":3}},"effectiveSpeakersByTurns":{"p10":4.1484,"p25":4.975,"median":6.3214,"p75":8.4454,"p90":10.879,"confidence95":{"low":6.0739,"high":6.4848}},"effectiveSpeakerShare":{"p10":0.07,"p25":0.0988,"median":0.1396,"p75":0.1915,"p90":0.2587,"confidence95":{"low":0.1341,"high":0.1453}},"speakerTurnGini":{"p10":0.6925,"p25":0.7375,"median":0.7764,"p75":0.8071,"p90":0.8308,"confidence95":{"low":0.7728,"high":0.7798}},"topOneTurnShare":{"p10":0.1934,"p25":0.2386,"median":0.3057,"p75":0.3689,"p90":0.4197,"confidence95":{"low":0.2981,"high":0.3143}},"topThreeTurnShare":{"p10":0.4277,"p25":0.5072,"median":0.5857,"p75":0.6672,"p90":0.7346,"confidence95":{"low":0.578,"high":0.5994}},"topFiveTurnShare":{"p10":0.5622,"p25":0.6352,"median":0.7179,"p75":0.7901,"p90":0.8492,"confidence95":{"low":0.7093,"high":0.7264}},"oneTurnSpeakerShare":{"p10":0.2,"p25":0.2679,"median":0.3571,"p75":0.4667,"p90":0.619,"confidence95":{"low":0.3438,"high":0.369}},"fiveOrFewerTurnSpeakerShare":{"p10":0.4815,"p25":0.5714,"median":0.6579,"p75":0.7424,"p90":0.8253,"confidence95":{"low":0.6475,"high":0.6667}},"singleDialogueSceneSpeakerShare":{"p10":0.4054,"p25":0.4808,"median":0.5714,"p75":0.6585,"p90":0.7464,"confidence95":{"low":0.5625,"high":0.5833}},"dialogueScenes":{"p10":51,"p25":69,"median":91,"p75":113,"p90":140,"confidence95":{"low":88,"high":93}},"medianSpeakersPerDialogueScene":{"p10":2,"p25":2,"median":2,"p75":2,"p90":3,"confidence95":{"low":2,"high":2}},"medianTurnsPerDialogueScene":{"p10":3,"p25":4,"median":5,"p75":7.5,"p90":11,"confidence95":{"low":5,"high":5.5}},"oneSpeakerSceneShare":{"p10":0.1211,"p25":0.1775,"median":0.2436,"p75":0.3271,"p90":0.397,"confidence95":{"low":0.2367,"high":0.25}},"twoSpeakerSceneShare":{"p10":0.2166,"p25":0.2974,"median":0.3757,"p75":0.4525,"p90":0.5165,"confidence95":{"low":0.3691,"high":0.3852}},"threePlusSpeakerSceneShare":{"p10":0.1919,"p25":0.2637,"median":0.3532,"p75":0.4576,"p90":0.5799,"confidence95":{"low":0.3452,"high":0.3636}},"speakerChangeRate":{"p10":0.7647,"p25":0.82,"median":0.8625,"p75":0.8975,"p90":0.9353,"confidence95":{"low":0.8575,"high":0.8674}},"uniqueAdjacentSpeakerPairs":{"p10":39,"p25":56,"median":78,"p75":111,"p90":160.7,"confidence95":{"low":75,"high":80}},"adjacentPairDensity":{"p10":0.0312,"p25":0.0485,"median":0.071,"p75":0.1003,"p90":0.1446,"confidence95":{"low":0.0672,"high":0.074}},"dominantAdjacentPairShare":{"p10":0.1006,"p25":0.1366,"median":0.1928,"p75":0.2741,"p90":0.3714,"confidence95":{"low":0.1827,"high":0.1997}},"effectiveAdjacentPairs":{"p10":5.471,"p25":8.3257,"median":12.966,"p75":19.3458,"p90":28.0768,"confidence95":{"low":12.1798,"high":13.5832}}},"sceneComposition":{"unitOfAnalysis":"One screenplay receives equal weight; each input is that screenplay's share of dialogue-bearing scenes.","meanShare":{"oneSpeaker":0.255,"twoSpeakers":0.3722,"threePlusSpeakers":0.3729}},"downloadVersion":"imsdb-0.2.0+cornell-0.1.0+concentration-1.0.0","relationships":{"analysisVersion":"0.2.0","analyzedAt":"2026-08-21","includedRecords":994,"method":{"correlation":"Spearman rank correlation across eligible screenplay-level measurements.","quartiles":"Quartiles are defined by speaking-character count; ties at a boundary remain together, so group sizes need not match exactly.","caution":"Pair-density correlation is strongly affected by its denominator: possible unordered pairs grow quadratically with raw cast size. It is retained as a structural diagnostic, not evidence that large casts are intrinsically less connected."},"correlations":{"rawCastVsEffectiveCast":{"n":994,"rho":0.4063},"rawCastVsEffectiveShare":{"n":994,"rho":-0.7017},"rawCastVsTopSpeakerShare":{"n":994,"rho":-0.2093},"rawCastVsTopThreeShare":{"n":994,"rho":-0.4463},"rawCastVsTurnInequality":{"n":994,"rho":0.2617},"rawCastVsMedianSpeakerTurns":{"n":994,"rho":-0.679},"rawCastVsOneTurnSpeakerShare":{"n":994,"rho":0.6248},"rawCastVsFiveOrFewerTurnSpeakerShare":{"n":994,"rho":0.7342},"rawCastVsSingleDialogueSceneSpeakerShare":{"n":994,"rho":0.6212},"rawCastVsPairDensity":{"n":994,"rho":-0.9237},"effectiveCastVsUniquePairs":{"n":994,"rho":0.5107},"twoSpeakerScenesVsDominantPair":{"n":994,"rho":0.3505}},"castQuartiles":[{"quartile":1,"n":256,"rawCastRange":{"low":null,"high":34},"medianSpeakingCharacters":27,"medianEffectiveSpeakersByTurns":5.1398,"medianEffectiveSpeakerShare":0.2038,"medianTopOneTurnShare":0.3349,"medianTopThreeTurnShare":0.6664,"medianMedianTurnsPerSpeaker":5,"medianOneTurnSpeakerShare":0.2647,"medianFiveOrFewerTurnSpeakerShare":0.5333,"medianSingleDialogueSceneSpeakerShare":0.4706,"medianAdjacentPairDensity":0.1289,"medianTwoSpeakerSceneShare":0.4197,"confidence95":{"effectiveSpeakersByTurns":{"low":4.9863,"high":5.4595},"fiveOrFewerTurnSpeakerShare":{"low":0.5251,"high":0.5588},"singleDialogueSceneSpeakerShare":{"low":0.4583,"high":0.4924}}},{"quartile":2,"n":258,"rawCastRange":{"low":34,"high":47},"medianSpeakingCharacters":41,"medianEffectiveSpeakersByTurns":6.2562,"medianEffectiveSpeakerShare":0.1553,"medianTopOneTurnShare":0.3031,"medianTopThreeTurnShare":0.5822,"medianMedianTurnsPerSpeaker":3,"medianOneTurnSpeakerShare":0.3213,"medianFiveOrFewerTurnSpeakerShare":0.6172,"medianSingleDialogueSceneSpeakerShare":0.5357,"medianAdjacentPairDensity":0.082,"medianTwoSpeakerSceneShare":0.4,"confidence95":{"effectiveSpeakersByTurns":{"low":5.9631,"high":6.8013},"fiveOrFewerTurnSpeakerShare":{"low":0.607,"high":0.6353},"singleDialogueSceneSpeakerShare":{"low":0.5222,"high":0.5541}}},{"quartile":3,"n":237,"rawCastRange":{"low":47,"high":66},"medianSpeakingCharacters":55,"medianEffectiveSpeakersByTurns":6.4788,"medianEffectiveSpeakerShare":0.1165,"medianTopOneTurnShare":0.3122,"medianTopThreeTurnShare":0.5759,"medianMedianTurnsPerSpeaker":2,"medianOneTurnSpeakerShare":0.381,"medianFiveOrFewerTurnSpeakerShare":0.6923,"medianSingleDialogueSceneSpeakerShare":0.6071,"medianAdjacentPairDensity":0.0586,"medianTwoSpeakerSceneShare":0.3677,"confidence95":{"effectiveSpeakersByTurns":{"low":6.0759,"high":6.8216},"fiveOrFewerTurnSpeakerShare":{"low":0.6735,"high":0.7083},"singleDialogueSceneSpeakerShare":{"low":0.5833,"high":0.62}}},{"quartile":4,"n":243,"rawCastRange":{"low":66,"high":null},"medianSpeakingCharacters":90,"medianEffectiveSpeakersByTurns":7.9922,"medianEffectiveSpeakerShare":0.0815,"medianTopOneTurnShare":0.2739,"medianTopThreeTurnShare":0.5154,"medianMedianTurnsPerSpeaker":1,"medianOneTurnSpeakerShare":0.5309,"medianFiveOrFewerTurnSpeakerShare":0.7944,"medianSingleDialogueSceneSpeakerShare":0.6907,"medianAdjacentPairDensity":0.0341,"medianTwoSpeakerSceneShare":0.2973,"confidence95":{"effectiveSpeakersByTurns":{"low":7.3074,"high":8.6418},"fiveOrFewerTurnSpeakerShare":{"low":0.7869,"high":0.8082},"singleDialogueSceneSpeakerShare":{"low":0.6739,"high":0.7083}}}]},"cornell":{"analysisVersion":"0.1.0","analyzedAt":"2026-09-18","corpus":{"name":"Cornell Movie-Dialogs Corpus","creators":"Cristian Danescu-Niculescu-Mizil and Lillian Lee","paper":"Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs (Workshop on Cognitive Modeling and Computational Linguistics, ACL 2011)","sourceUrl":"https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html","files":{"lines":{"name":"movie_lines.txt","sha256":"59b9a78482829bc083d69cc9c164fc058eb4d0431712e09a4b08059663d0de56"},"conversations":{"name":"movie_conversations.txt","sha256":"600bc1d34ca629533643ca85c14b18849a548dce663e6d36977c14f24b75e055"},"characters":{"name":"movie_characters_metadata.txt","sha256":"332f1c58198ed1a6fef3c1b13bc54b46730a401a11ae979b7601e1f1564aaf23"},"titles":{"name":"movie_titles_metadata.txt","sha256":"da1c5f3fbf66caf50d6fa1b2d88d1e77389e84de4bb2a77793c6db79e17efb1a"}},"encoding":"latin1","films":617,"titleRows":617,"characters":9035,"utterances":304713,"zeroWordUtterances":274,"words":3210011,"conversations":83097},"method":{"tokenizer":"Unicode NFC letters and digits with internal apostrophes; hyphens separate tokens; underscores are not word characters. Zero-word rows stay in the corpus totals and leave every length denominator.","bootstrap":{"statistic":"equal-film mean","interval":"percentile 95%","replicates":5000,"seed":20260918},"caveats":["The corpus is sampled dialogue from scripts the authors could collect, not complete screenplays; utterance and conversation counts are not scene or page counts.","Gender and credit position are the authors' cast-list labels and cover a third of characters; the coverage figures say exactly which words each cut rests on.","An exchange is what the corpus recorded as one conversation. It does not assert scene boundaries, interruptions or addressee beyond the two listed characters.","These are corpus descriptions, not writing rules."]},"utteranceLength":{"unitOfAnalysis":"Pooled figures treat every word-bearing utterance equally; equal-film figures give each of the 617 films one vote.","wordBearingUtterances":304439,"pooled":{"p10":2,"p25":4,"median":7,"p75":13,"p90":23,"mean":10.544},"perFilmMedianWords":{"p10":5,"p25":6,"median":7,"p75":8,"p90":9},"longUtteranceThresholdWords":30,"overThreshold":{"pooledUtteranceShare":0.0542,"pooledWordShare":0.243,"equalFilmMeanWordShare":0.2237,"equalFilmConfidence95":{"low":0.2144,"high":0.2329}},"longestDecile":{"pooledWordShare":0.3568,"equalFilmMeanWordShare":0.3442}},"exchangeStructure":{"unitOfAnalysis":"One conversation in movie_conversations.txt is one exchange between two characters; its turns are the listed line IDs in order.","conversations":83097,"missingLineReferences":0,"adjacentUtterancePairs":221616,"turnsPerConversation":{"p10":2,"p25":2,"median":3,"p75":4,"p90":7,"mean":3.667,"max":89},"exactlyTwoTurnsShare":0.4584,"strictAlternationShare":0.9927,"wordsPerConversation":{"p10":8,"p25":14,"median":26,"p75":47,"p90":82},"longestTurnWordShare":{"p10":0.3208,"p25":0.4375,"median":0.5714,"p75":0.7097,"p90":0.8333},"dominantFloorThreshold":0.7,"dominatedShare":0.4848,"genderPairing":{"coverage":{"conversationsWithBothLabeled":52038,"shareOfConversations":0.6262,"shareOfWords":0.6634},"conversationShare":{"twoWomen":0.0602,"mixed":0.4916,"twoMen":0.4482},"wordShare":{"twoWomen":0.0579,"mixed":0.4851,"twoMen":0.457}}},"castLabels":{"labelSource":"Credited gender and credit position are the corpus's own character metadata, derived by its authors from cast lists. Every figure states the coverage it rests on.","characters":9035,"gendered":{"women":966,"men":2049,"total":3015},"creditPositioned":2679,"coverage":{"genderedCharacterShare":0.3337,"genderedUtteranceShare":0.7943,"genderedWordShare":0.7887,"creditPositionedWordShare":0.7022},"byGender":{"unitOfAnalysis":"Pooled over every utterance by a gender-labeled character.","wordShare":{"women":0.2812,"men":0.7188},"utteranceShare":{"women":0.2944,"men":0.7056},"medianWordsPerCharacter":{"women":515,"men":623}},"perFilm":{"unitOfAnalysis":"Films with at least one woman and one man among their labeled characters; the share is women's words over all labeled words in that film.","filmsWithBothLabels":519,"femaleWordShare":{"p10":0.1084,"p25":0.1731,"median":0.2727,"p75":0.4254,"p90":0.5747},"femaleMajorityFilmShare":0.1715},"creditPosition":[{"bucket":"1","characters":497,"wordShare":0.3538,"medianWordsPerCharacter":1431,"femaleShareOfCharacters":0.1791,"femaleShareOfWords":0.1693},{"bucket":"2","characters":443,"wordShare":0.2155,"medianWordsPerCharacter":906,"femaleShareOfCharacters":0.4763,"femaleShareOfWords":0.4704},{"bucket":"3","characters":352,"wordShare":0.1206,"medianWordsPerCharacter":649.5,"femaleShareOfCharacters":0.3409,"femaleShareOfWords":0.3153},{"bucket":"4-5","characters":479,"wordShare":0.124,"medianWordsPerCharacter":483,"femaleShareOfCharacters":0.2818,"femaleShareOfWords":0.2607},{"bucket":"6+","characters":908,"wordShare":0.1862,"medianWordsPerCharacter":337,"femaleShareOfCharacters":0.3359,"femaleShareOfWords":0.2944}],"topBilled":{"characters":497,"women":89,"men":408,"medianShareOfFilmLabeledWords":{"women":0.3603,"men":0.3959}}}},"concentration":{"version":"1.0.0","created":"2026-09-17","source":"Bundled Cornell-derived numeric utterance projection; source text not redistributed","unit":"Word-bearing sampled utterance; movie is the resampling cluster","input_sha256":"2fa524ae8e866bd980012f45a8d189baa6b0154bc368a8e1ff454e6d2b7ad9d0","all_rows":304713,"positive_rows":304439,"excluded_zero_word_rows":274,"films":617,"pooled":{"n":304439,"words":3210011,"gini":0.49006306,"top_decile_count":30444,"top_decile_word_share_pct":35.68022041,"lorenz":[[0,0],[5,0.47420242],[10,1.21154725],[15,2.1599521],[20,3.57149555],[25,5.13995123],[30,7.03676093],[35,9.17767104],[40,11.54868317],[45,14.34893214],[50,17.40765063],[55,20.83184762],[60,24.72114893],[65,29.14505589],[70,34.15683934],[75,39.95750326],[80,46.6628619],[85,54.61366643],[90,64.31985124],[95,76.94072076],[100,100]]},"thresholds":[{"threshold_words_exclusive":7,"turn_count":140361,"word_count":2568214,"pooled_turn_share_pct":46.1048026,"pooled_word_share_pct":80.0063925,"equal_film_turn_share_pct":46.69200605,"equal_film_word_share_pct":78.94030977,"equal_film_turn_ci95":[45.96879376,47.39985488],"equal_film_word_ci95":[78.36984405,79.49222346],"perFilm":{"p10":69.9921037220439,"median":79.9572192513369,"p90":86.88587496777492}},{"threshold_words_exclusive":15,"turn_count":59868,"word_count":1696831,"pooled_turn_share_pct":19.66502321,"pooled_word_share_pct":52.86059767,"equal_film_turn_share_pct":20.02555878,"equal_film_word_share_pct":50.91756572,"equal_film_turn_ci95":[19.46756587,20.57613584],"equal_film_word_ci95":[49.99501582,51.8068415],"perFilm":{"p10":36.317176063590054,"median":51.22834238427722,"p90":64.5454860310259}},{"threshold_words_exclusive":23,"turn_count":28899,"word_count":1109804,"pooled_turn_share_pct":9.49254202,"pooled_word_share_pct":34.57321486,"equal_film_turn_share_pct":9.657776,"equal_film_word_share_pct":32.51840631,"equal_film_turn_ci95":[9.28437644,10.02533323],"equal_film_word_ci95":[31.56604261,33.44734502],"perFilm":{"p10":17.15048788993829,"median":31.83118741058655,"p90":47.798229779766416}},{"threshold_words_exclusive":30,"turn_count":16499,"word_count":779930,"pooled_turn_share_pct":5.41947648,"pooled_word_share_pct":24.29680148,"equal_film_turn_share_pct":5.52296058,"equal_film_word_share_pct":22.37454362,"equal_film_turn_ci95":[5.23619969,5.81234784],"equal_film_word_ci95":[21.46921336,23.27642765],"perFilm":{"p10":7.853209891052176,"median":21.51208106001559,"p90":36.66383246880445}},{"threshold_words_exclusive":40,"turn_count":8206,"word_count":490960,"pooled_turn_share_pct":2.69544966,"pooled_word_share_pct":15.29465164,"equal_film_turn_share_pct":2.7448224,"equal_film_word_share_pct":13.7585268,"equal_film_turn_ci95":[2.56247069,2.93620341],"equal_film_word_ci95":[12.99863981,14.51702602],"perFilm":{"p10":2.726142109990926,"median":12.06157443491816,"p90":25.980753888504506}},{"threshold_words_exclusive":60,"turn_count":2572,"word_count":219760,"pooled_turn_share_pct":0.84483263,"pooled_word_share_pct":6.84608246,"equal_film_turn_share_pct":0.86347666,"equal_film_word_share_pct":5.95958894,"equal_film_turn_ci95":[0.77129872,0.96369206],"equal_film_word_ci95":[5.4332551,6.50492879],"perFilm":{"p10":0,"median":4.220045214770158,"p90":13.900472757120582}}],"bootstrap":{"unit":"film","replicates":5000,"seed":20260917,"statistic":"mean of film-specific proportions","interval":"percentile, 2.5th and 97.5th percentiles","interpretation":"Observed-film resampling stability, not population-representative uncertainty"},"restrictions":["No full-screenplay completeness claim","No performance duration inference","No professional quality score","No scene-order inference from row order"]}}