{
  "meta": {
    "dataset_version": "1.1.0",
    "parser_version": "1.2.0",
    "tag_rules_version": "1.1.0",
    "source_title": "张一鸣微博日记2286条",
    "pdf_pages": 355,
    "cover_claimed_records": 2286,
    "parsed_timestamp_records": 2171,
    "difference_vs_cover": -115,
    "coverage_vs_cover": 0.9497,
    "date_start": "2010-04-29",
    "date_end": "2016-03-25",
    "unavailable_or_deleted_notice_records": 200,
    "unavailable_or_deleted_notice_rate": 0.0921,
    "same_text_multi_record_groups": 7,
    "same_text_multi_record_records": 22,
    "active_days": 934,
    "records_per_active_day": 2.32,
    "records_2010_2012": 1790,
    "records_2010_2012_rate": 0.8245,
    "core_non_share_unique_records": 1417,
    "share_records_with_author_note": 520,
    "share_split_confidence": {
      "high": 683,
      "low": 38,
      "medium": 21
    }
  },
  "yearly": [
    {
      "year": 2010,
      "records": 544,
      "share_records": 118,
      "share_rate": 0.2169,
      "share_rate_ci95": [
        0.1843,
        0.2535
      ],
      "non_share_unique_records": 421,
      "median_chars_non_share": 67,
      "mobile_rate": 0.0717,
      "mobile_rate_ci95": [
        0.0529,
        0.0965
      ],
      "toutiao_source_rate": 0.0,
      "toutiao_source_rate_ci95": [
        0.0,
        0.007
      ],
      "first_person_rate_non_share": 0.4442,
      "question_rate_non_share": 0.1069,
      "english_rate_non_share": 0.4561
    },
    {
      "year": 2011,
      "records": 625,
      "share_records": 177,
      "share_rate": 0.2832,
      "share_rate_ci95": [
        0.2493,
        0.3198
      ],
      "non_share_unique_records": 444,
      "median_chars_non_share": 53.5,
      "mobile_rate": 0.168,
      "mobile_rate_ci95": [
        0.1407,
        0.1993
      ],
      "toutiao_source_rate": 0.0016,
      "toutiao_source_rate_ci95": [
        0.0003,
        0.009
      ],
      "first_person_rate_non_share": 0.3896,
      "question_rate_non_share": 0.0923,
      "english_rate_non_share": 0.4054
    },
    {
      "year": 2012,
      "records": 621,
      "share_records": 234,
      "share_rate": 0.3768,
      "share_rate_ci95": [
        0.3396,
        0.4156
      ],
      "non_share_unique_records": 385,
      "median_chars_non_share": 54,
      "mobile_rate": 0.1514,
      "mobile_rate_ci95": [
        0.1253,
        0.1817
      ],
      "toutiao_source_rate": 0.1546,
      "toutiao_source_rate_ci95": [
        0.1283,
        0.1851
      ],
      "first_person_rate_non_share": 0.3792,
      "question_rate_non_share": 0.1091,
      "english_rate_non_share": 0.4364
    },
    {
      "year": 2013,
      "records": 295,
      "share_records": 189,
      "share_rate": 0.6407,
      "share_rate_ci95": [
        0.5844,
        0.6933
      ],
      "non_share_unique_records": 106,
      "median_chars_non_share": 45.0,
      "mobile_rate": 0.2441,
      "mobile_rate_ci95": [
        0.1985,
        0.2962
      ],
      "toutiao_source_rate": 0.4915,
      "toutiao_source_rate_ci95": [
        0.435,
        0.5483
      ],
      "first_person_rate_non_share": 0.3019,
      "question_rate_non_share": 0.1698,
      "english_rate_non_share": 0.4245
    },
    {
      "year": 2014,
      "records": 38,
      "share_records": 21,
      "share_rate": 0.5526,
      "share_rate_ci95": [
        0.3971,
        0.6985
      ],
      "non_share_unique_records": 16,
      "median_chars_non_share": 82.0,
      "mobile_rate": 0.3684,
      "mobile_rate_ci95": [
        0.2338,
        0.5272
      ],
      "toutiao_source_rate": 0.4737,
      "toutiao_source_rate_ci95": [
        0.3248,
        0.6274
      ],
      "first_person_rate_non_share": 0.5625,
      "question_rate_non_share": 0.125,
      "english_rate_non_share": 0.5625
    },
    {
      "year": 2015,
      "records": 47,
      "share_records": 3,
      "share_rate": 0.0638,
      "share_rate_ci95": [
        0.0219,
        0.1716
      ],
      "non_share_unique_records": 44,
      "median_chars_non_share": 56.0,
      "mobile_rate": 0.7234,
      "mobile_rate_ci95": [
        0.5824,
        0.8306
      ],
      "toutiao_source_rate": 0.0213,
      "toutiao_source_rate_ci95": [
        0.0038,
        0.1111
      ],
      "first_person_rate_non_share": 0.3636,
      "question_rate_non_share": 0.1136,
      "english_rate_non_share": 0.3182
    },
    {
      "year": 2016,
      "records": 1,
      "share_records": 0,
      "share_rate": 0.0,
      "share_rate_ci95": [
        0.0,
        0.7935
      ],
      "non_share_unique_records": 1,
      "median_chars_non_share": 80,
      "mobile_rate": 0.0,
      "mobile_rate_ci95": [
        0.0,
        0.7935
      ],
      "toutiao_source_rate": 0.0,
      "toutiao_source_rate_ci95": [
        0.0,
        0.7935
      ],
      "first_person_rate_non_share": 0.0,
      "question_rate_non_share": 0.0,
      "english_rate_non_share": 0.0
    }
  ],
  "monthly": [
    {
      "month": "2010-04",
      "records": 3
    },
    {
      "month": "2010-05",
      "records": 36
    },
    {
      "month": "2010-06",
      "records": 60
    },
    {
      "month": "2010-07",
      "records": 82
    },
    {
      "month": "2010-08",
      "records": 57
    },
    {
      "month": "2010-09",
      "records": 69
    },
    {
      "month": "2010-10",
      "records": 76
    },
    {
      "month": "2010-11",
      "records": 90
    },
    {
      "month": "2010-12",
      "records": 71
    },
    {
      "month": "2011-01",
      "records": 66
    },
    {
      "month": "2011-02",
      "records": 73
    },
    {
      "month": "2011-03",
      "records": 74
    },
    {
      "month": "2011-04",
      "records": 44
    },
    {
      "month": "2011-05",
      "records": 53
    },
    {
      "month": "2011-06",
      "records": 60
    },
    {
      "month": "2011-07",
      "records": 29
    },
    {
      "month": "2011-08",
      "records": 34
    },
    {
      "month": "2011-09",
      "records": 60
    },
    {
      "month": "2011-10",
      "records": 55
    },
    {
      "month": "2011-11",
      "records": 29
    },
    {
      "month": "2011-12",
      "records": 48
    },
    {
      "month": "2012-01",
      "records": 60
    },
    {
      "month": "2012-02",
      "records": 68
    },
    {
      "month": "2012-03",
      "records": 52
    },
    {
      "month": "2012-04",
      "records": 71
    },
    {
      "month": "2012-05",
      "records": 35
    },
    {
      "month": "2012-06",
      "records": 47
    },
    {
      "month": "2012-07",
      "records": 43
    },
    {
      "month": "2012-08",
      "records": 54
    },
    {
      "month": "2012-09",
      "records": 60
    },
    {
      "month": "2012-10",
      "records": 40
    },
    {
      "month": "2012-11",
      "records": 39
    },
    {
      "month": "2012-12",
      "records": 52
    },
    {
      "month": "2013-01",
      "records": 63
    },
    {
      "month": "2013-02",
      "records": 49
    },
    {
      "month": "2013-03",
      "records": 70
    },
    {
      "month": "2013-04",
      "records": 27
    },
    {
      "month": "2013-05",
      "records": 28
    },
    {
      "month": "2013-06",
      "records": 16
    },
    {
      "month": "2013-07",
      "records": 9
    },
    {
      "month": "2013-08",
      "records": 9
    },
    {
      "month": "2013-09",
      "records": 6
    },
    {
      "month": "2013-10",
      "records": 6
    },
    {
      "month": "2013-11",
      "records": 4
    },
    {
      "month": "2013-12",
      "records": 8
    },
    {
      "month": "2014-01",
      "records": 3
    },
    {
      "month": "2014-02",
      "records": 4
    },
    {
      "month": "2014-03",
      "records": 6
    },
    {
      "month": "2014-04",
      "records": 1
    },
    {
      "month": "2014-05",
      "records": 3
    },
    {
      "month": "2014-06",
      "records": 2
    },
    {
      "month": "2014-07",
      "records": 2
    },
    {
      "month": "2014-08",
      "records": 7
    },
    {
      "month": "2014-09",
      "records": 2
    },
    {
      "month": "2014-10",
      "records": 1
    },
    {
      "month": "2014-11",
      "records": 3
    },
    {
      "month": "2014-12",
      "records": 4
    },
    {
      "month": "2015-01",
      "records": 4
    },
    {
      "month": "2015-02",
      "records": 1
    },
    {
      "month": "2015-03",
      "records": 2
    },
    {
      "month": "2015-04",
      "records": 17
    },
    {
      "month": "2015-05",
      "records": 7
    },
    {
      "month": "2015-06",
      "records": 2
    },
    {
      "month": "2015-07",
      "records": 0
    },
    {
      "month": "2015-08",
      "records": 6
    },
    {
      "month": "2015-09",
      "records": 4
    },
    {
      "month": "2015-10",
      "records": 2
    },
    {
      "month": "2015-11",
      "records": 2
    },
    {
      "month": "2015-12",
      "records": 0
    },
    {
      "month": "2016-01",
      "records": 0
    },
    {
      "month": "2016-02",
      "records": 0
    },
    {
      "month": "2016-03",
      "records": 1
    }
  ],
  "hours": [
    {
      "hour": 0,
      "count": 245
    },
    {
      "hour": 1,
      "count": 107
    },
    {
      "hour": 2,
      "count": 22
    },
    {
      "hour": 3,
      "count": 4
    },
    {
      "hour": 4,
      "count": 1
    },
    {
      "hour": 5,
      "count": 1
    },
    {
      "hour": 6,
      "count": 4
    },
    {
      "hour": 7,
      "count": 12
    },
    {
      "hour": 8,
      "count": 21
    },
    {
      "hour": 9,
      "count": 88
    },
    {
      "hour": 10,
      "count": 80
    },
    {
      "hour": 11,
      "count": 71
    },
    {
      "hour": 12,
      "count": 100
    },
    {
      "hour": 13,
      "count": 135
    },
    {
      "hour": 14,
      "count": 92
    },
    {
      "hour": 15,
      "count": 80
    },
    {
      "hour": 16,
      "count": 66
    },
    {
      "hour": 17,
      "count": 66
    },
    {
      "hour": 18,
      "count": 117
    },
    {
      "hour": 19,
      "count": 109
    },
    {
      "hour": 20,
      "count": 131
    },
    {
      "hour": 21,
      "count": 177
    },
    {
      "hour": 22,
      "count": 214
    },
    {
      "hour": 23,
      "count": 228
    }
  ],
  "weekdays": [
    {
      "weekday": "周一",
      "index": 0,
      "count": 253
    },
    {
      "weekday": "周二",
      "index": 1,
      "count": 273
    },
    {
      "weekday": "周三",
      "index": 2,
      "count": 299
    },
    {
      "weekday": "周四",
      "index": 3,
      "count": 316
    },
    {
      "weekday": "周五",
      "index": 4,
      "count": 296
    },
    {
      "weekday": "周六",
      "index": 5,
      "count": 364
    },
    {
      "weekday": "周日",
      "index": 6,
      "count": 370
    }
  ],
  "heatmap": {
    "weekdays": [
      "周一",
      "周二",
      "周三",
      "周四",
      "周五",
      "周六",
      "周日"
    ],
    "matrix": [
      [
        30,
        14,
        2,
        0,
        0,
        0,
        1,
        0,
        3,
        10,
        7,
        4,
        3,
        15,
        8,
        7,
        10,
        8,
        14,
        17,
        10,
        17,
        40,
        33
      ],
      [
        37,
        10,
        2,
        2,
        0,
        0,
        0,
        3,
        3,
        10,
        8,
        6,
        21,
        18,
        12,
        7,
        6,
        8,
        14,
        8,
        19,
        26,
        24,
        29
      ],
      [
        31,
        11,
        9,
        0,
        0,
        0,
        2,
        0,
        6,
        12,
        14,
        7,
        23,
        17,
        14,
        10,
        4,
        8,
        15,
        12,
        17,
        27,
        34,
        26
      ],
      [
        32,
        6,
        1,
        0,
        0,
        0,
        1,
        4,
        3,
        18,
        11,
        6,
        10,
        22,
        15,
        13,
        9,
        10,
        14,
        19,
        19,
        28,
        33,
        42
      ],
      [
        35,
        17,
        0,
        0,
        1,
        0,
        0,
        3,
        2,
        14,
        11,
        13,
        12,
        23,
        14,
        9,
        8,
        5,
        17,
        14,
        21,
        18,
        27,
        32
      ],
      [
        25,
        20,
        5,
        1,
        0,
        0,
        0,
        0,
        4,
        11,
        13,
        21,
        20,
        21,
        12,
        14,
        11,
        18,
        25,
        20,
        24,
        32,
        35,
        32
      ],
      [
        55,
        29,
        3,
        1,
        0,
        1,
        0,
        2,
        0,
        13,
        16,
        14,
        11,
        19,
        17,
        20,
        18,
        9,
        18,
        19,
        21,
        29,
        21,
        34
      ]
    ]
  },
  "sources": [
    {
      "source": "微博 weibo.com",
      "count": 1491,
      "rate": 0.6868
    },
    {
      "source": "iPhone 客户端",
      "count": 281,
      "rate": 0.1294
    },
    {
      "source": "今日头条",
      "count": 261,
      "rate": 0.1202
    },
    {
      "source": "手机微博触屏版",
      "count": 22,
      "rate": 0.0101
    },
    {
      "source": "Android 客户端",
      "count": 19,
      "rate": 0.0088
    },
    {
      "source": "微博手机版",
      "count": 16,
      "rate": 0.0074
    },
    {
      "source": "微博搜索",
      "count": 11,
      "rate": 0.0051
    },
    {
      "source": "专业版微博",
      "count": 9,
      "rate": 0.0041
    },
    {
      "source": "房产资讯",
      "count": 9,
      "rate": 0.0041
    },
    {
      "source": "iPhone 6",
      "count": 8,
      "rate": 0.0037
    },
    {
      "source": "iPhone 6 Plus",
      "count": 5,
      "rate": 0.0023
    },
    {
      "source": "iPad 客户端",
      "count": 5,
      "rate": 0.0023
    },
    {
      "source": "微博浏览器插件",
      "count": 5,
      "rate": 0.0023
    },
    {
      "source": "豆瓣电影",
      "count": 4,
      "rate": 0.0018
    },
    {
      "source": "iPhone 6s",
      "count": 2,
      "rate": 0.0009
    }
  ],
  "source_groups": [
    "微博网页/工具",
    "移动端",
    "今日头条分享",
    "豆瓣",
    "其他"
  ],
  "source_by_year": [
    {
      "year": 2010,
      "微博网页/工具": 504,
      "移动端": 39,
      "今日头条分享": 0,
      "豆瓣": 0,
      "其他": 1
    },
    {
      "year": 2011,
      "微博网页/工具": 500,
      "移动端": 105,
      "今日头条分享": 1,
      "豆瓣": 0,
      "其他": 19
    },
    {
      "year": 2012,
      "微博网页/工具": 422,
      "移动端": 94,
      "今日头条分享": 96,
      "豆瓣": 4,
      "其他": 5
    },
    {
      "year": 2013,
      "微博网页/工具": 76,
      "移动端": 72,
      "今日头条分享": 145,
      "豆瓣": 1,
      "其他": 1
    },
    {
      "year": 2014,
      "微博网页/工具": 5,
      "移动端": 14,
      "今日头条分享": 18,
      "豆瓣": 0,
      "其他": 1
    },
    {
      "year": 2015,
      "微博网页/工具": 11,
      "移动端": 34,
      "今日头条分享": 1,
      "豆瓣": 1,
      "其他": 0
    },
    {
      "year": 2016,
      "微博网页/工具": 1,
      "移动端": 0,
      "今日头条分享": 0,
      "豆瓣": 0,
      "其他": 0
    }
  ],
  "length": {
    "population": "未识别为转发/分享、且正文不完全重复的记录",
    "n": 1417,
    "mean": 74.1,
    "median": 58,
    "p10": 19.0,
    "p25": 32.0,
    "p75": 109.0,
    "p90": 152.0,
    "p95": 179.0,
    "bins": [
      {
        "label": "1–20",
        "count": 166,
        "rate": 0.1171
      },
      {
        "label": "21–50",
        "count": 477,
        "rate": 0.3366
      },
      {
        "label": "51–100",
        "count": 370,
        "rate": 0.2611
      },
      {
        "label": "101–200",
        "count": 371,
        "rate": 0.2618
      },
      {
        "label": "201–500",
        "count": 33,
        "rate": 0.0233
      },
      {
        "label": "501+",
        "count": 0,
        "rate": 0.0
      }
    ]
  },
  "linguistic_features": [
    {
      "feature": "含第一人称（我/自己/本人）",
      "count": 563,
      "rate": 0.3973
    },
    {
      "feature": "含问号",
      "count": 153,
      "rate": 0.108
    },
    {
      "feature": "含连续英文字符",
      "count": 608,
      "rate": 0.4291
    },
    {
      "feature": "含数字",
      "count": 431,
      "rate": 0.3042
    }
  ],
  "intervals": {
    "median_hours": 7.57,
    "p90_hours": 45.29,
    "max_days": 128.79
  },
  "phrases_exploratory": [
    {
      "phrase": "公司",
      "occurrences": 210,
      "cohesion": 5.646,
      "score": 30.218
    },
    {
      "phrase": "团队",
      "occurrences": 111,
      "cohesion": 6.387,
      "score": 30.138
    },
    {
      "phrase": "技术",
      "occurrences": 90,
      "cohesion": 6.498,
      "score": 29.311
    },
    {
      "phrase": "朋友",
      "occurrences": 92,
      "cohesion": 6.442,
      "score": 29.201
    },
    {
      "phrase": "自己",
      "occurrences": 174,
      "cohesion": 5.631,
      "score": 29.081
    },
    {
      "phrase": "问题",
      "occurrences": 111,
      "cohesion": 6.08,
      "score": 28.691
    },
    {
      "phrase": "产品",
      "occurrences": 156,
      "cohesion": 5.657,
      "score": 28.604
    },
    {
      "phrase": "推荐",
      "occurrences": 70,
      "cohesion": 6.676,
      "score": 28.459
    },
    {
      "phrase": "搜索",
      "occurrences": 65,
      "cohesion": 6.664,
      "score": 27.92
    },
    {
      "phrase": "希望",
      "occurrences": 49,
      "cohesion": 7.012,
      "score": 27.432
    },
    {
      "phrase": "喜欢",
      "occurrences": 57,
      "cohesion": 6.696,
      "score": 27.187
    },
    {
      "phrase": "招聘",
      "occurrences": 40,
      "cohesion": 7.162,
      "score": 26.597
    },
    {
      "phrase": "今天",
      "occurrences": 147,
      "cohesion": 5.26,
      "score": 26.283
    },
    {
      "phrase": "互联",
      "occurrences": 67,
      "cohesion": 6.224,
      "score": 26.264
    },
    {
      "phrase": "北京",
      "occurrences": 41,
      "cohesion": 7.006,
      "score": 26.188
    },
    {
      "phrase": "应该",
      "occurrences": 80,
      "cohesion": 5.925,
      "score": 26.038
    },
    {
      "phrase": "创业",
      "occurrences": 127,
      "cohesion": 5.317,
      "score": 25.799
    },
    {
      "phrase": "工作",
      "occurrences": 121,
      "cohesion": 5.283,
      "score": 25.379
    },
    {
      "phrase": "服务",
      "occurrences": 45,
      "cohesion": 6.61,
      "score": 25.309
    },
    {
      "phrase": "豆瓣",
      "occurrences": 20,
      "cohesion": 8.231,
      "score": 25.059
    },
    {
      "phrase": "游戏",
      "occurrences": 26,
      "cohesion": 7.574,
      "score": 24.961
    },
    {
      "phrase": "广告",
      "occurrences": 43,
      "cohesion": 6.589,
      "score": 24.935
    },
    {
      "phrase": "选择",
      "occurrences": 30,
      "cohesion": 7.223,
      "score": 24.805
    },
    {
      "phrase": "分享",
      "occurrences": 67,
      "cohesion": 5.848,
      "score": 24.676
    },
    {
      "phrase": "信息",
      "occurrences": 62,
      "cohesion": 5.952,
      "score": 24.661
    },
    {
      "phrase": "腾讯",
      "occurrences": 38,
      "cohesion": 6.651,
      "score": 24.366
    },
    {
      "phrase": "视频",
      "occurrences": 35,
      "cohesion": 6.773,
      "score": 24.273
    },
    {
      "phrase": "状态",
      "occurrences": 31,
      "cohesion": 6.986,
      "score": 24.211
    },
    {
      "phrase": "互联网",
      "occurrences": 64,
      "cohesion": 5.788,
      "score": 24.162
    },
    {
      "phrase": "东西",
      "occurrences": 31,
      "cohesion": 6.964,
      "score": 24.137
    }
  ],
  "year_terms_exploratory": [
    {
      "year": 2010,
      "terms": [
        {
          "phrase": "状态",
          "year_count": 25,
          "rest_count": 8,
          "z": 5.78
        },
        {
          "phrase": "锻炼",
          "year_count": 16,
          "rest_count": 3,
          "z": 5.2
        },
        {
          "phrase": "创业",
          "year_count": 67,
          "rest_count": 69,
          "z": 4.99
        },
        {
          "phrase": "团队",
          "year_count": 60,
          "rest_count": 61,
          "z": 4.78
        },
        {
          "phrase": "身体",
          "year_count": 15,
          "rest_count": 4,
          "z": 4.69
        },
        {
          "phrase": "同事",
          "year_count": 32,
          "rest_count": 25,
          "z": 4.36
        },
        {
          "phrase": "退休",
          "year_count": 8,
          "rest_count": 0,
          "z": 4.35
        },
        {
          "phrase": "耐心",
          "year_count": 13,
          "rest_count": 5,
          "z": 3.94
        }
      ]
    },
    {
      "year": 2011,
      "terms": [
        {
          "phrase": "资讯",
          "year_count": 26,
          "rest_count": 2,
          "z": 7.18
        },
        {
          "phrase": "房产",
          "year_count": 33,
          "rest_count": 9,
          "z": 6.79
        },
        {
          "phrase": "房产资讯",
          "year_count": 17,
          "rest_count": 0,
          "z": 6.24
        },
        {
          "phrase": "九九房",
          "year_count": 30,
          "rest_count": 10,
          "z": 6.13
        },
        {
          "phrase": "买房",
          "year_count": 15,
          "rest_count": 2,
          "z": 5.18
        },
        {
          "phrase": "房源",
          "year_count": 14,
          "rest_count": 2,
          "z": 4.96
        },
        {
          "phrase": "租房",
          "year_count": 15,
          "rest_count": 5,
          "z": 4.34
        },
        {
          "phrase": "资金",
          "year_count": 8,
          "rest_count": 0,
          "z": 4.28
        }
      ]
    },
    {
      "year": 2012,
      "terms": [
        {
          "phrase": "产品",
          "year_count": 78,
          "rest_count": 103,
          "z": 5.31
        },
        {
          "phrase": "刷榜",
          "year_count": 8,
          "rest_count": 0,
          "z": 4.79
        },
        {
          "phrase": "样子",
          "year_count": 13,
          "rest_count": 4,
          "z": 4.77
        },
        {
          "phrase": "知乎",
          "year_count": 9,
          "rest_count": 1,
          "z": 4.64
        },
        {
          "phrase": "好朋友",
          "year_count": 7,
          "rest_count": 0,
          "z": 4.48
        },
        {
          "phrase": "微信",
          "year_count": 16,
          "rest_count": 10,
          "z": 4.16
        },
        {
          "phrase": "广告",
          "year_count": 25,
          "rest_count": 23,
          "z": 4.16
        },
        {
          "phrase": "厦门",
          "year_count": 6,
          "rest_count": 0,
          "z": 4.15
        }
      ]
    },
    {
      "year": 2013,
      "terms": [
        {
          "phrase": "习近平",
          "year_count": 6,
          "rest_count": 0,
          "z": 7.88
        },
        {
          "phrase": "空气",
          "year_count": 6,
          "rest_count": 0,
          "z": 7.88
        },
        {
          "phrase": "日头条",
          "year_count": 9,
          "rest_count": 5,
          "z": 7.32
        },
        {
          "phrase": "科技产",
          "year_count": 5,
          "rest_count": 0,
          "z": 7.19
        },
        {
          "phrase": "刺猬",
          "year_count": 5,
          "rest_count": 0,
          "z": 7.19
        },
        {
          "phrase": "今日头条",
          "year_count": 8,
          "rest_count": 5,
          "z": 6.7
        },
        {
          "phrase": "科技产品",
          "year_count": 4,
          "rest_count": 0,
          "z": 6.43
        },
        {
          "phrase": "小米路",
          "year_count": 4,
          "rest_count": 0,
          "z": 6.43
        }
      ]
    },
    {
      "year": 2014,
      "terms": [
        {
          "phrase": "罕见病",
          "year_count": 7,
          "rest_count": 0,
          "z": 19.74
        },
        {
          "phrase": "二次创业",
          "year_count": 5,
          "rest_count": 1,
          "z": 15.18
        },
        {
          "phrase": "动信息流",
          "year_count": 4,
          "rest_count": 0,
          "z": 14.92
        },
        {
          "phrase": "游戏引",
          "year_count": 4,
          "rest_count": 0,
          "z": 14.92
        },
        {
          "phrase": "流动",
          "year_count": 4,
          "rest_count": 1,
          "z": 13.29
        },
        {
          "phrase": "联手",
          "year_count": 4,
          "rest_count": 1,
          "z": 13.29
        },
        {
          "phrase": "启动信息",
          "year_count": 3,
          "rest_count": 0,
          "z": 12.92
        },
        {
          "phrase": "信息流优",
          "year_count": 3,
          "rest_count": 0,
          "z": 12.92
        }
      ]
    },
    {
      "year": 2015,
      "terms": [
        {
          "phrase": "头条号",
          "year_count": 5,
          "rest_count": 0,
          "z": 12.06
        },
        {
          "phrase": "头条",
          "year_count": 12,
          "rest_count": 15,
          "z": 11.92
        },
        {
          "phrase": "创作",
          "year_count": 5,
          "rest_count": 1,
          "z": 10.93
        },
        {
          "phrase": "演讲",
          "year_count": 8,
          "rest_count": 7,
          "z": 10.8
        },
        {
          "phrase": "品技术人",
          "year_count": 4,
          "rest_count": 0,
          "z": 10.79
        },
        {
          "phrase": "同理心",
          "year_count": 4,
          "rest_count": 0,
          "z": 10.79
        },
        {
          "phrase": "青年",
          "year_count": 4,
          "rest_count": 1,
          "z": 9.56
        },
        {
          "phrase": "求知",
          "year_count": 4,
          "rest_count": 1,
          "z": 9.56
        }
      ]
    }
  ],
  "method": {
    "record_unit": "每个匹配“YYYY-M-D HH:MM 来自 …”的时间戳视为一条记录。",
    "share_rule": "仅当正文出现显式“转发微博/ //@ ”标记，或来源为“今日头条/正文标记分享自今日头条”时，记为转发/分享。",
    "author_quote_rule": "转发记录用可观察分隔符拆成“作者附言”和“转发正文”；无法可靠拆分时保守地把整段放入转发正文，不归因给作者。主题标签只依据作者附言生成。",
    "length_rule": "移除页码、采集广告、作者名单独行与平台删除/不可见提示后，计算非空白字符数。长度分析进一步排除显式转发/分享与完全相同正文的多记录。",
    "source_rule": "来源按 PDF 时间戳行中的“来自”字段解析，并归为微博网页/工具、移动端、今日头条分享、豆瓣、其他。",
    "ci_rule": "年度比例同时给出 Wilson 95% 置信区间；它只表达有限样本下比例估计的不确定性，不修复语料缺失或选择偏差。",
    "phrase_rule": "实验性短语挖掘：对非分享文本抽取2–4字中文n-gram，以出现次数×最小切分凝聚度（PMI-like）排序；该结果不等同于主题分类。",
    "timezone": "PDF 未声明时区；所有小时/星期统计按文件中显示的本地时间直接计算，不做时区转换。",
    "limitations": [
      "封面称2286条，但正文仅识别到2171个符合时间戳格式的记录；因此不能把该PDF视作完整微博全集。",
      "部分记录含删除/不可见提示；采集文本可能保留链接标题、被截断内容或不完整转发正文。",
      "作者附言/转发正文拆分是确定性启发式规则；低置信度记录保守地不把文本归因给作者。",
      "“转发/分享”是保守的规则识别，不等于对原创权或作者身份的判断。",
      "2014–2016样本量显著变小；即使提供Wilson区间，也不能消除语料覆盖变化造成的偏差。",
      "规则主题标签尚未完成人工金标准验证，因此只用于浏览筛选，不报告分类准确率。",
      "词组挖掘不使用中文分词词典，适合发现重复搭配，不应被解释为心理特征或价值取向。"
    ]
  }
}