{
 "@context": "https://schema.org",
 "@type": "ScholarlyArticle",
 "@id": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#paper",
 "aboutThisFile": {
  "whatThisIs": "A research brief: a structured summary of one paper, prepared for seanrintel.com from the paper's full text.",
  "howItWasMade": "This brief was prepared with AI assistance and published by Sean Rintel. It is not the authors' published text.",
  "whatIsVerbatim": "Only 'quote' fields, figure captions and 'abstract' are the authors' own words. Research questions follow the paper's wording where it states them. Takeaway, summaries, answers, definitions and method are the site's plain-language paraphrase.",
  "howItIsChecked": "Before publication every quote is matched against the paper and every number in the brief is found in it. 'verified' is the date of the last check.",
  "howToUse": [
   "For a quick answer, use 'takeaway' and 'questions'. For evidence, use 'findings' (each has a verbatim quote, its location in the paper and a 'url' anchored to that finding on the paper's page).",
   "Locations such as '§5.2, p. 9' refer to the version at 'pageNumbersReferTo'.",
   "For anything not covered here, read the paper itself: 'fullTextSources' lists free versions first.",
   "If 'researchOverview' is present, the paper is part of one of Sean Rintel's research overviews: it gives the overview's thesis, the claims this paper is evidence for and its role in each, and the other papers in the overview.",
   "To find other papers by Sean Rintel, use the catalogue at https://seanrintel.com/publications/index.json."
  ],
  "authorship": "Sean Rintel's role on each paper: lead author when he is first author, sole author when he is the only author, and otherwise senior author. Senior author here means the senior researcher on the team, whatever his position in the author list.",
  "howToCite": "Cite the paper, not this file: use 'citation' or the ready-made 'bibtex' (DOI where given) and name every author. Attribute paraphrase to the paper's findings, and use quotation marks only for 'quote' text."
 },
 "name": "Automated mapping of competitive and collaborative overlapping talk in video meetings",
 "author": [
  {
   "@type": "Person",
   "name": "Eleni Margariti"
  },
  {
   "@type": "Person",
   "@id": "https://seanrintel.com/#sean-rintel",
   "name": "Sean Rintel",
   "url": "https://seanrintel.com/",
   "sameAs": [
    "https://orcid.org/0000-0003-0840-0546",
    "https://scholar.google.com/citations?user=xc25GRgAAAAJ",
    "https://www.wikidata.org/wiki/Q102369654",
    "https://www.microsoft.com/en-us/research/people/serintel/",
    "https://www.linkedin.com/in/seanrintel"
   ]
  },
  {
   "@type": "Person",
   "name": "Brendan Murphy"
  },
  {
   "@type": "Person",
   "name": "Abigail Sellen"
  }
 ],
 "datePublished": "2022-04",
 "doi": "10.1145/3491101.3519612",
 "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html",
 "citation": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612",
 "bibtex": "@inproceedings{margariti2022automated,\nauthor = {Margariti, Eleni and Rintel, Sean and Murphy, Brendan and Sellen, Abigail},\ntitle = {Automated mapping of competitive and collaborative overlapping talk in video meetings},\norganization = {ACM},\nbooktitle = {CHI EA 2022},\nyear = {2022},\nmonth = {April},\nurl = {https://doi.org/10.1145/3491101.3519612},\nnote = {CHI ’22 Extended Abstracts},\ndoi = {10.1145/3491101.3519612},\n}",
 "abstract": "Video meetings are notorious for difficulties with conversational turn-taking, which has impacts on inclusion and outcomes. We present a scalable automatic process to categorize turn-taking patterns in remote meetings based on eyes-off analysis of meeting transcripts. Drawing on a series of remote meetings (10 series, 34 total meetings) recorded in July-August 2021 by employees of a global technology company, we identified and parametrized patterns of cooperative and competitive overlaps of turns. The results show initial success characterizing people’s behaviours as either likely to continue or cede turns based on either the amount of overlap that they produce during other’s turns or the amount of overlap they experience in their own turns. With further development and validation, this method could be used to measure inclusion in remote and hybrid meetings.",
 "fullTextSources": [
  {
   "kind": "freeAccess",
   "url": "https://doi.org/10.1145/3491101.3519612",
   "label": "DOI (Free Access)"
  },
  {
   "kind": "freeAccess",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.pdf",
   "label": "Author's Copy"
  }
 ],
 "fullTextAvailable": true,
 "takeaway": "Transcript timing alone can partly map turn-taking in video meetings, showing who keeps or cedes the floor when talked over. But cooperative overlaps (backchannels like 'uh huh') and competitive bids for the floor can look alike, because timing without content cannot show what an overlap is doing.",
 "whyItMatters": {
  "stateOfTheArt": {
   "summary": "Turn-taking has long been quantified, but mostly from audio corpora or small controlled experiments, and often without considering privacy constraints.",
   "quote": "most prior work focuses on audio conversations, builds upon speech and audio datasets [19, 21] or reflects on controlled experiments in a limited number of meetings",
   "location": "§2.2, p. 2"
  },
  "contribution": {
   "summary": "What is new is the input and the safeguard. Ordinary, de-identified Microsoft Teams transcripts are processed automatically, so turn-taking can be studied across an organisation's real meetings without audio recordings and without anyone reading what was said.",
   "quote": "We contribute to prior work by presenting a GDPR-compliant method to detect cooperative competitive overlaps by automatically processing meeting transcripts as the input dataset instead of speech and audio corpora.",
   "location": "§2.2, p. 2"
  },
  "whoCares": {
   "summary": "Organisations wanting insight into meeting practices and inclusion, and researchers building meeting analytics for remote and hybrid meetings.",
   "quote": "Meeting analytics may assist organisations improve meeting practices by providing insights on turn-taking behaviour.",
   "location": "§1, p. 1"
  }
 },
 "researchQuestions": [
  "How can cooperative competitive overlaps be automatically identified based on eyes-off processing of meeting transcripts?"
 ],
 "concepts": [
  {
   "term": "Cooperative overlap",
   "definition": "Talk over another speaker that supports them, such as backchannels and acknowledgement tokens, rather than taking the floor.",
   "quote": "provide attention, understanding, or agreement, rather than substantive content",
   "location": "§2.1, p. 2"
  },
  {
   "term": "Competitive overlap",
   "definition": "The contrast with cooperative overlap, as defined in the conversation-analysis literature:",
   "quote": "Competitive overlaps are those in which listeners use various ways of taking the floor from current speakers",
   "location": "§2.1, p. 2"
  },
  {
   "term": "Overtake",
   "definition": "A change of speaker. The paper's focus is the competitive kind:",
   "quote": "competitive overtakes (changes of speakers that happen with an overlap)",
   "location": "§1, p. 1"
  },
  {
   "term": "Eyes-off analysis",
   "definition": "A privacy safeguard: transcripts were processed automatically for timing and speaker data only.",
   "quote": "The researchers had no access to the transcript content",
   "location": "§3.1, p. 3"
  }
 ],
 "method": {
  "design": "Development of an automated process. Overlap patterns were first identified visually and with conversation-analytic methods on some of the authors' own meetings, then parametrised from turn-length statistics and applied automatically to the full dataset.",
  "setting": "Regular project/status meetings held on Microsoft Teams in a global technology company, using Teams' automatic speaker-attributed, time-stamped transcripts, processed by a custom application that de-identified participants.",
  "sample": "A convenience sample of three project groups, n∼52 participants. 10 meeting series, 34 meetings, recorded July-August 2021.",
  "n": 52,
  "analysis": "Descriptive statistics of turn, overlap and overtake durations. Turns parametrised as speech of 3s or more. Overlaps and gaps below 0.24s (an estimated return delay) excluded as indeterminate. Probabilities of continuing or ceding a turn under different overlap patterns."
 },
 "findings": [
  {
   "headline": "Meetings move fast.",
   "summary": "In some of the authors' own Teams meetings, used to develop the method, the median transcribed turn lasted under two and a half seconds (a fast-paced conversation). The transcription service also produced many very short utterances of one or two words.",
   "quote": "Median of turns was placed at ∼2.4s (Median=2.38s, Mean=4.37s, Sd=5.146) indicating a fastpasted conversation.",
   "location": "§4.1, p. 3",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-1-p-3",
   "cite": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612 (§4.1, p. 3)"
  },
  {
   "headline": "Timing cannot always reveal intent.",
   "summary": "Working from timing and speaker labels alone, some overlap patterns could be classed with reasonable confidence. For example, a long overlap at the start of a turn strongly indicates competition for the floor. Others stayed ambiguous:",
   "quote": "Pattern 6, a repeated overlap, may be a competitive attempt to take a turn or a cooperative backchannel.",
   "location": "§4.1, p. 3",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-1-p-3-2",
   "cite": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612 (§4.1, p. 3)"
  },
  {
   "headline": "Uninterrupted speakers usually carry on.",
   "summary": "Across all 34 meetings, a speaker whom nobody talked over was about twice as likely to keep talking as to hand over to someone else.",
   "quote": "initiating a turn is twice as likely to continue their turn than to allow someone else to take over when no overlap occurs during this turn",
   "location": "§4.2, p. 6",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-6",
   "cite": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612 (§4.2, p. 6)"
  },
  {
   "headline": "One overlap changes the odds.",
   "summary": "When one other participant talked over a speaker once, the speaker became almost as likely to cede the turn to that person as to continue, with ceding slightly less likely.",
   "quote": "This illustrates that the impact of a single overlap is significant.",
   "location": "§4.2, p. 6",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-6-2",
   "cite": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612 (§4.2, p. 6)"
  },
  {
   "headline": "Persistent overlapping makes a takeover more likely.",
   "summary": "When one person talked over a speaker repeatedly within the same turn, that person taking over became more likely than the speaker carrying on. Such repeated overlaps may be bids for the floor, some of them rejected.",
   "quote": "This case includes a potential attempt to take turn, and whether an overtake is achieved or not.",
   "location": "§4.2, p. 6",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-6-3",
   "cite": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612 (§4.2, p. 6)"
  },
  {
   "headline": "Hints of individual turn-taking styles.",
   "summary": "In one meeting series, participants differed sharply. Those most likely to keep their turn when talked over once were not the same as those who kept it under repeated overlaps. Consistent differences like these point towards individual turn-taking profiles.",
   "quote": "In the case of multiple overlaps occurring (Figure 3 C), the same participants presented the opposite behaviour, with P3 always abandoning turn",
   "location": "§4.2, p. 5",
   "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-5",
   "cite": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612 (§4.2, p. 5)"
  }
 ],
 "questions": [
  {
   "question": "Can software detect interruptions in video meetings without anyone reading what was said?",
   "answer": "Partly. The method uses only the timing and speaker labels in automatic meeting transcripts, never their content, keeping it privacy-preserving and scalable. These alone revealed recurring overlap patterns and their effect on who held the floor. Timing alone cannot always tell a supportive overlap from a bid to take over.",
   "source": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612",
   "basedOn": [
    {
     "location": "§4.1, p. 3",
     "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-1-p-3-2"
    },
    {
     "location": "§4.2, p. 6",
     "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-6-2"
    },
    {
     "location": "§4.2, p. 6",
     "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-6-3"
    }
   ]
  },
  {
   "question": "Is talking over someone always an interruption?",
   "answer": "No. Conversation analysts distinguish cooperative overlaps, such as 'mm' or 'yeah', which show attention or agreement, from competitive ones that take the floor. Repeated overlaps can be either (encouragement or insistent bidding for a turn), so the two have to be modelled together.",
   "source": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612",
   "basedOn": [
    {
     "location": "§4.1, p. 3",
     "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-1-p-3-2"
    }
   ]
  },
  {
   "question": "Do people have their own styles of handling being talked over?",
   "answer": "It appears so, though the evidence is thin. In one meeting series, the participant most likely to keep talking after a single overlap always gave up the turn under repeated overlaps, and also talked over others most. Whether such turn-taking profiles hold across meetings needs a much larger dataset.",
   "source": "Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612",
   "basedOn": [
    {
     "location": "§4.2, p. 5",
     "url": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.html#at-s4-2-p-5"
    }
   ]
  }
 ],
 "cites": [
  {
   "url": "https://seanrintel.com/publications/hybrid-meetings-in-the-modern-workplace-stories-of-success-and-failure.html",
   "title": "Hybrid Meetings in the Modern Workplace: Stories of Success and Failure",
   "location": "p. 8"
  },
  {
   "url": "https://seanrintel.com/publications/large-scale-analysis-of-multitasking-behavior-during-remote-meetings.html",
   "title": "Large Scale Analysis of Multitasking Behavior During Remote Meetings",
   "location": "p. 7"
  },
  {
   "url": "https://seanrintel.com/publications/reconfiguring-hybrid-meetings-moving-from-user-centered-design-to-meeting-centered-design.html",
   "title": "(Re)Configuring Hybrid Meetings: Moving from User-Centered Design to Meeting-Centered Design",
   "location": "p. 8"
  }
 ],
 "quantitative": [
  {
   "measure": "Dataset",
   "value": "10 series, 34 total meetings",
   "location": "Abstract, p. 1"
  },
  {
   "measure": "Estimated return delay; overlaps and gaps below it excluded",
   "value": "∼0.24s; 9% of all data",
   "location": "§3.2, p. 3"
  },
  {
   "measure": "Turn length in the initial meetings",
   "value": "Median=2.38s, Mean=4.37s, Sd=5.146",
   "location": "§4.1, p. 3"
  },
  {
   "measure": "Overtakes, and overtakes with a determined overlap (3s turn size)",
   "value": "18%; 15%",
   "location": "§4.2, p. 4"
  },
  {
   "measure": "No overlap: continuing the turn vs letting someone take over",
   "value": "Mean= 63.51% vs Mean= 31.2%",
   "location": "§4.2, p. 6"
  },
  {
   "measure": "Repeated overlaps by one person: overtake vs turn continues vs another speaker takes over",
   "value": "Mean =19.57% vs Mean=12.00% vs Mean= 2.63%",
   "location": "§4.2, p. 6"
  }
 ],
 "implications": [
  {
   "summary": "The method lays a basis for assessing meeting inclusion from metrics such as overtakes with overlap and rejected attempts to take a turn.",
   "quote": "This work provides the basis for assessing meeting inclusion based on a combination of metrics",
   "location": "§5, p. 7"
  },
  {
   "summary": "Possible profiles of inclusive and non-inclusive participation, for individuals and groups, but only with meeting context such as function and roles.",
   "quote": "this should not be judged prematurely without further insight into the meeting's context (function, role of attendees)",
   "location": "§5, p. 7"
  },
  {
   "summary": "Profiling needs careful ethical and privacy safeguards. Labelling behaviours can harm individuals.",
   "quote": "linking behaviours such competitiveness or domination with race or gender should be avoided",
   "location": "§5, p. 7"
  },
  {
   "summary": "With in-room speaker attribution, the analysis could be extended to hybrid meetings to measure the impact of being remote or local.",
   "quote": "it may be possible to measure the impact of being remote or local in a hybrid meeting",
   "location": "§5, p. 7"
  }
 ],
 "limitations": [
  {
   "summary": "Results are promising but initial, from a small dataset that needs validation with a larger sample.",
   "quote": "this work shows promising initial results using a small dataset, which need to be validated with a larger data sample",
   "location": "§7, p. 7"
  },
  {
   "summary": "Speech-to-text and transcript timing constrain accuracy. Latency makes very small overlaps and gaps indeterminate."
  },
  {
   "summary": "Other telemetry, such as mute/unmute, reactions, raised hands and meeting chat, was not used and could broaden understanding of turn-taking.",
   "quote": "application telemetry such as mute/unmute, reactions, raise hands, and, in particular, the use of the meeting's text chat",
   "location": "§7, p. 7"
  }
 ],
 "figures": [
  {
   "src": "https://seanrintel.com/publications/figures/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings/fig-3.webp",
   "caption": "Figure 3: Turn-taking behaviour in a Meeting Series (ID=4)",
   "alt": "Six bar charts (A to F) for one meeting series, one bar per participant: how often each continued or gave up a turn with no, one or repeated overlaps, and how often each took over after overlapping others.",
   "location": "Fig. 3, p. 6",
   "credit": "Figure 3 from Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612"
  },
  {
   "src": "https://seanrintel.com/publications/figures/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings/fig-1.webp",
   "caption": "Figure 1: Patterns 5: Isolated overlap; 4: Overtake with overlap; 6: repeated overlap; 7: overlap at the end of turn",
   "alt": "Time-stamped transcript excerpt from two speakers with overlap durations and analyst notes, above a timeline of their speech segments with boxes marking overlap patterns 4, 5, 6 and 7.",
   "location": "Fig. 1, p. 4",
   "credit": "Figure 1 from Eleni Margariti, Sean Rintel, Brendan Murphy, and Abigail Sellen. 2022. Automated mapping of competitive and collaborative overlapping talk in video meetings. CHI EA 2022. https://doi.org/10.1145/3491101.3519612"
  }
 ],
 "pageNumbersReferTo": "https://seanrintel.com/publications/automated-mapping-of-competitive-and-collaborative-overlapping-talk-in-video-meetings.pdf",
 "verified": "2026-10-25",
 "studyFigure": {
  "about": "The opening figure on this paper's page, made for the site with AI assistance from this verified brief. It is not the paper's own figure. Evidence entries index this file's quantitative, findings and limitations arrays.",
  "study": {
   "kind": "single",
   "summary": "Development of an automated method for mapping overlapping talk, applied to the Microsoft Teams transcripts of 34 project meetings in ten series at a global technology company. About 52 people took part, recorded in July and August 2021.",
   "steps": [
    {
     "label": "Three project groups",
     "detail": "About 52 people in three project groups held regular project and status meetings by video."
    },
    {
     "label": "34 video meetings",
     "detail": "Ten meeting series were recorded, with automatic transcripts that label each speaker and time each utterance."
    },
    {
     "label": "Patterns found by hand",
     "detail": "The authors first identified overlap patterns by eye and with conversation analysis in some of their own meetings."
    },
    {
     "label": "Rules applied to all",
     "detail": "Those patterns became rules, applied automatically to all 34 meetings without anyone reading what was said."
    }
   ]
  },
  "tool": {
   "heading": "The method",
   "steps": [
    {
     "title": "De-identify transcripts",
     "text": "A custom application removes participants' identities and keeps who spoke when."
    },
    {
     "title": "Mark turns",
     "text": "Speech lasting 3 seconds or more counts as a turn."
    },
    {
     "title": "Set aside tiny overlaps",
     "text": "Overlaps and gaps under 0.24 seconds, an estimated timing delay, are too short to judge. These were 9% of the data."
    },
    {
     "title": "Classify each overlap",
     "text": "Each overlap is matched to a pattern by its timing, such as a long overlap at a turn's start or a repeated overlap.",
     "part": true
    },
    {
     "title": "Count outcomes",
     "text": "For each pattern, the method counts how often the speaker kept the turn or someone else took over.",
     "part": true
    }
   ]
  },
  "findings": {
   "legend": null,
   "stages": [
    {
     "title": "Reading intent from timing",
     "sub": "what speaker timing alone could and could not show",
     "items": [
      {
       "dir": "none",
       "text": "In the authors' own meetings, the median turn lasted about 2.4 seconds.",
       "detail": "The median is the middle value. Talk was fast paced, and the transcription produced many utterances of one or two words.",
       "evidence": [
        "quantitative[2]",
        "findings[0]"
       ]
      },
      {
       "dir": "none",
       "text": "From timing alone, a long overlap at a turn's start strongly signalled a bid for the floor.",
       "detail": "Some overlap patterns could be classed with reasonable confidence from timing and speaker labels, without the words.",
       "evidence": [
        "findings[1]"
       ]
      },
      {
       "dir": "none",
       "text": "From timing alone, a repeated overlap could be a floor bid or a supportive uh huh.",
       "detail": "A supportive uh huh is a backchannel, a short listener response. Timing without the words cannot always show what an overlap is doing.",
       "evidence": [
        "findings[1]",
        "takeaway"
       ]
      }
     ]
    },
    {
     "title": "Keeping or ceding the floor",
     "sub": "odds across all 34 meetings",
     "items": [
      {
       "dir": "none",
       "text": "In 34 video meetings, speakers nobody talked over kept talking about twice as often as handing over.",
       "detail": "On average, 63.51% of such turns continued and 31.2% passed to someone else.",
       "evidence": [
        "quantitative[4]",
        "findings[2]"
       ]
      },
      {
       "dir": "none",
       "text": "In 34 video meetings, speakers talked over once became almost as likely to cede as to continue.",
       "detail": "Ceding the turn to the person who overlapped stayed slightly less likely than carrying on.",
       "evidence": [
        "findings[3]"
       ]
      },
      {
       "dir": "none",
       "text": "In 34 video meetings, repeated overlapping by one person made a takeover likelier than the speaker continuing.",
       "detail": "On average, 19.57% of such turns ended in a takeover, against 12.00% where the speaker carried on. Some repeated overlaps may be failed bids for the floor.",
       "evidence": [
        "quantitative[5]",
        "findings[4]"
       ]
      }
     ]
    },
    {
     "title": "Individual styles",
     "sub": "one meeting series, and the limits of the data",
     "items": [
      {
       "dir": "none",
       "text": "In one meeting series, participants differed sharply in keeping their turn when talked over.",
       "detail": "Those who kept their turn after one overlap were not those who kept it under repeated overlaps. The paper suggests this points to individual turn-taking profiles.",
       "evidence": [
        "findings[5]"
       ]
      },
      {
       "dir": "none",
       "text": "The authors describe these results as promising but initial, from a small dataset.",
       "detail": "The results need validating with a larger sample. Transcript timing limits accuracy, so very small overlaps and gaps could not be judged.",
       "evidence": [
        "limitations[0]",
        "limitations[1]"
       ]
      }
     ]
    }
   ]
  },
  "keyTerm": "competitive overlap",
  "takeaway": "Speaker timing in transcripts can map who keeps or cedes the floor without reading the words. Timing alone may not tell cooperative from competitive overlap."
 }
}