Skip to content

Instantly share code, notes, and snippets.

@richshaw

richshaw/Example1.bson

Created June 27, 2014 14:08
Show Gist options
  • Save richshaw/b668f27465c71ae9a186 to your computer and use it in GitHub Desktop.
Save richshaw/b668f27465c71ae9a186 to your computer and use it in GitHub Desktop.
Download ZIP
Bot content data structure examples
Raw
README.md

Examples of bot content data structure for partners and the curious.

Raw
Example1.bson
{
_id: ObjectId("525db371b1e6020700000001"),
bot_id: "525db35a18f354a034000000",
link: "http://www.guernicamag.com/features/the-naked-man/",
link_hash: "21eb41e9cfca527d9827084db5953e22c9742d4a653fab9c23dabb58be9d6aa4",
source: "primal",
created: ISODate("2013-10-15T21:28:08.033Z"),
content: "An, er, intimate reconsideration of male nudity.",
title: "The Naked Man",
type: "news",
publisher: "www.guernicamag.com",
query: {
query: "man/modern",
source: "primal"
},
meta: {
alchemy: {
language: {
language: "english",
"iso-639-1": "en",
"iso-639-2": "eng",
"iso-639-3": "eng",
ethnologue: "http://www.ethnologue.com/show_language.asp?code=eng",
"native-speakers": "309-400 million",
wikipedia: "http://en.wikipedia.org/wiki/English_language"
},
keywords: [
{
text: "naked man",
relevance: 0.917756,
sentiment: {
type: "negative",
score: -0.00785193
}
},
{
text: "male nudity",
relevance: 0.915385,
sentiment: {
type: "negative",
score: -0.0113717
}
},
{
text: "intimate reconsideration",
relevance: 0.852454,
sentiment: {
type: "negative",
score: -0.0116445
}
}
],
sentiment: {
type: "negative",
score: -0.0104079
},
entities: [
{
type: "JobTitle",
relevance: 0.867027,
sentiment: {
type: "negative",
score: -0.0210623,
mixed: "1"
},
count: 5,
text: "writer"
},
{
type: "Person",
relevance: 0.56348,
sentiment: {
type: "neutral"
},
count: 2,
text: "anthony weiner",
disambiguated: {
subType: [
"Politician",
"Celebrity",
"U.S.Congressperson"
],
name: "Anthony Weiner",
website: "http://www.house.gov/weiner/",
dbpedia: "http://dbpedia.org/resource/Anthony_Weiner",
freebase: "http://rdf.freebase.com/ns/m.03tvfr"
}
},
{
type: "Person",
relevance: 0.527493,
sentiment: {
type: "positive",
score: 0.18243
},
count: 2,
text: "kanye west",
disambiguated: {
subType: [
"MusicalArtist"
],
name: "Kanye West",
dbpedia: "http://dbpedia.org/resource/Kanye_West",
freebase: "http://rdf.freebase.com/ns/m.02l840",
yago: "http://yago-knowledge.org/resource/Kanye_West",
musicBrainz: "http://zitgist.com/music/artist/164f0d73-1234-4e2c-8743-d77bf2191051"
}
},
{
type: "Person",
relevance: 0.522906,
sentiment: {
type: "positive",
score: 0.0913785
},
count: 2,
text: "brett favre",
disambiguated: {
subType: [
"Athlete",
"AwardWinner",
"Celebrity",
"FootballPlayer",
"SportsLeagueAwardWinner",
"TVActor"
],
name: "Brett Favre",
website: "http://www.officialbrettfavre.com",
dbpedia: "http://dbpedia.org/resource/Brett_Favre",
freebase: "http://rdf.freebase.com/ns/m.0cv72h",
opencyc: "http://sw.opencyc.org/concept/Mx4rv8ZpxpwpEbGdrcN5Y29ycA",
yago: "http://yago-knowledge.org/resource/Brett_Favre"
}
},
{
type: "City",
relevance: 0.484087,
sentiment: {
type: "negative",
score: -0.558937,
mixed: "1"
},
count: 2,
text: "philistinism"
}
],
relations: [
{
subject: {
text: "I"
},
action: {
text: "hoped",
lemmatized: "hope",
verb: {
text: "hope",
tense: "past"
}
},
object: {
text: "that a series of naked pictures of a writer, presented in a short essay collection on a variety of mostly nonsexual subjects, would be a hallmark of how a naked body welcomes erotic adornments and postures but can never be defined by them, especially when viewed in context of the subject’s writing",
sentiment: {
type: "negative",
score: -0.0415943
},
sentimentFromSubject: {
type: "positive",
score: "0.356222"
},
entities: [
{
type: "JobTitle",
text: "writer"
}
]
}
},
{
subject: {
text: "a series of naked pictures of a writer",
entities: [
{
type: "JobTitle",
text: "writer"
}
]
},
action: {
text: "presented",
lemmatized: "present",
verb: {
text: "present",
tense: "past"
}
},
location: {
text: "in a short essay collection on a variety of mostly nonsexual subjects",
sentiment: {
type: "negative",
score: -0.0804048
}
}
},
{
subject: {
text: "I"
},
action: {
text: "called",
lemmatized: "call",
verb: {
text: "call",
tense: "past"
}
},
object: {
text: "the essay collection Poshlost, a Russian word Vladimir Nabokov defined as “corny trash, vulgar clichés",
sentiment: {
type: "negative",
score: -0.164087
},
entities: [
{
type: "Person",
text: "Poshlost"
},
{
type: "Person",
text: "Vladimir Nabokov",
disambiguated: {
subType: [
"Person",
"Writer",
"AwardNominee",
"FilmWriter"
],
name: "Vladimir Nabokov",
website: "http://www.libraries.psu.edu/nabokov/zembla.htm",
dbpedia: "http://dbpedia.org/resource/Vladimir_Nabokov",
freebase: "http://rdf.freebase.com/ns/m.03f47xl",
opencyc: "http://sw.opencyc.org/concept/Mx4rv_qcrJwpEbGdrcN5Y29ycA",
yago: "http://yago-knowledge.org/resource/Vladimir_Nabokov",
musicBrainz: "http://zitgist.com/music/artist/9e3f4dc0-f90b-4ead-9aa3-7c5b56dd5826"
}
}
]
}
},
{
subject: {
text: "Vladimir Nabokov",
entities: [
{
type: "Person",
text: "Vladimir Nabokov",
disambiguated: {
subType: [
"Person",
"Writer",
"AwardNominee",
"FilmWriter"
],
name: "Vladimir Nabokov",
website: "http://www.libraries.psu.edu/nabokov/zembla.htm",
dbpedia: "http://dbpedia.org/resource/Vladimir_Nabokov",
freebase: "http://rdf.freebase.com/ns/m.03f47xl",
opencyc: "http://sw.opencyc.org/concept/Mx4rv_qcrJwpEbGdrcN5Y29ycA",
yago: "http://yago-knowledge.org/resource/Vladimir_Nabokov",
musicBrainz: "http://zitgist.com/music/artist/9e3f4dc0-f90b-4ead-9aa3-7c5b56dd5826"
}
}
]
},
action: {
text: "defined",
lemmatized: "define",
verb: {
text: "define",
tense: "past"
}
},
object: {
text: "a Russian word"
}
},
{
subject: {
text: "imitations of imitations, bogus profundities, crude, moronic, and dishonest pseudo-literature.” Nowhere",
sentiment: {
type: "negative",
score: -0.0744818
}
},
action: {
text: "are",
lemmatized: "be",
verb: {
text: "be",
tense: "present"
}
},
object: {
text: "these qualities more entrenched than in pornography",
sentiment: {
type: "negative",
score: -0.0471324
},
entities: [
{
type: "City",
text: "Philistinism"
}
]
}
}
]
},
embedly: {
url: "http://www.guernicamag.com/features/the-naked-man/",
type: "html",
provider_name: "Guernicamag",
provider_url: "http://www.guernicamag.com",
provider_display: "www.guernicamag.com",
description: "In the modern redux, penis is patriarchy, and patriarchy is violence. But must to show one's penis be to endorse power and privilege? An ...",
title: "The Naked Man",
media: {
url: "http://guernica.wpengine.netdna-cdn.com/wp-content/uploads/2013/09/DSC_0174-copy-e1379178525511.jpg",
type: "photo"
}
},
google: {
esp: [
{
label: "none",
score: "0.468204"
},
{
label: "personal",
score: "0.184004"
},
{
label: "social",
score: "0.177123"
},
{
label: "environmental",
score: "0.170668"
}
]
}
},
content_original: "An, er, intimate reconsideration of male nudity."
}
Raw
Example2.bson
{
_id: ObjectId("51f7eeed0acd020700000001"),
bot_id: "51f7eed73874879f7d00006c",
link: "http://www.amazon.com/dp/1437714161/?tag=priafusi-20",
link_hash: "d631b0fc18a02cc7b90c40aad89d23c99f249a4b34dd985da394ce6ab897cf12",
source: "primal",
created: ISODate("2013-07-30T16:50:43.000Z"),
content: "Featuring analysis of healthcare issues and first-person stories, Policy & Politics in Nursing and Health Care helps you develop skills in influencing policy in today's changing health care environment. Approximately 150 expert",
title: "Policy & Politics in Nursing and Health Care, 6e (Policy and Politics in Nursing and ...",
type: "product",
publisher: "www.amazon.com",
query: {
query: "policy",
source: "primal",
contentSource: "PrimalSources/Books"
},
meta: {
alchemy: {
language: {
language: "english",
"iso-639-1": "en",
"iso-639-2": "eng",
"iso-639-3": "eng",
ethnologue: "http://www.ethnologue.com/show_language.asp?code=eng",
"native-speakers": "309-400 million",
wikipedia: "http://en.wikipedia.org/wiki/English_language"
},
keywords: [
{
text: "health care",
relevance: 0.929987,
sentiment: {
type: "positive",
score: 0.373042
}
},
{
text: "policy",
relevance: 0.763866,
sentiment: {
type: "positive",
score: 0.346572
}
},
{
text: "politics",
relevance: 0.629028,
sentiment: {
type: "positive",
score: 0.295325
}
},
{
text: "health care environment",
relevance: 0.612867,
sentiment: {
type: "positive",
score: 0.247741
}
},
{
text: "first-person stories",
relevance: 0.510035,
sentiment: {
type: "positive",
score: 0.237138
}
}
],
sentiment: {
type: "positive",
score: 0.0973655,
mixed: "1"
},
entities: [
{
type: "Degree",
relevance: 0.866526,
sentiment: {
type: "positive",
score: 0.690351
},
count: 5,
text: "nursing and health"
},
{
type: "JobTitle",
relevance: 0.74788,
sentiment: {
type: "positive",
score: 0.466996
},
count: 5,
text: "health care"
},
{
type: "FieldTerminology",
relevance: 0.412108,
sentiment: {
type: "positive",
score: 0.688119
},
count: 1,
text: "health care reform"
},
{
type: "FieldTerminology",
relevance: 0.38916,
sentiment: {
type: "positive",
score: 0.662116
},
count: 2,
text: "health care system"
},
{
type: "PrintMedia",
relevance: 0.375194,
sentiment: {
type: "positive",
score: 0.0344745
},
count: 1,
text: "american journal of nursing"
}
],
relations: [
{
subject: {
text: "Policy & Politics in Nursing and Health Care",
entities: [
{
type: "JobTitle",
text: "Health Care"
}
]
},
action: {
text: "Featuring",
lemmatized: "Featuring",
verb: {
text: "Featuring",
tense: "present"
}
},
object: {
text: "analysis of healthcare issues and first-person stories"
}
},
{
subject: {
text: "Policy & Politics in Nursing and Health Care",
entities: [
{
type: "JobTitle",
text: "Health Care"
}
]
},
action: {
text: "helps",
lemmatized: "help",
verb: {
text: "help",
tense: "present"
}
},
object: {
text: "you develop skills in influencing policy in today's changing health care environment",
sentiment: {
type: "positive",
score: 0.222351
},
sentimentFromSubject: {
type: "positive",
score: "0.260827"
}
}
},
{
subject: {
text: "by nursing leaders who influenced health care reform with the Patient Protection and Affordable Care Act of 2010",
sentiment: {
type: "positive",
score: 0.23368
},
entities: [
{
type: "FieldTerminology",
text: "health care reform"
}
]
},
action: {
text: "are provided",
lemmatized: "be provide",
verb: {
text: "provide",
tense: "past"
}
},
object: {
text: "The latest information and perspectives"
}
},
{
subject: {
text: "nursing leaders"
},
action: {
text: "influenced",
lemmatized: "influence",
verb: {
text: "influence",
tense: "past"
}
},
object: {
text: "health care reform",
entities: [
{
type: "FieldTerminology",
text: "health care reform"
}
]
}
},
{
subject: {
text: "Kevin MacDonald | 2 reviewers",
entities: [
{
type: "Person",
text: "Kevin MacDonald"
}
]
},
action: {
text: "made",
lemmatized: "make",
verb: {
text: "make",
tense: "past"
}
},
object: {
text: "a similar statement"
}
}
]
},
embedly: {
url: "http://www.amazon.com/dp/1437714161/?tag=priafusi-20",
type: "html",
provider_name: "Amazon",
provider_url: "http://www.amazon.com",
provider_display: "www.amazon.com",
description: "Policy & Politics in Nursing and Health Care, 6e (Policy and Politics in Nursing and Health) [Diana J. Mason RN PhD FAAN, Judith K ...",
title: "Policy & Politics in Nursing and Health Care, 6e (Policy and Politics in Nursing and Health)",
media: {
url: "http://ecx.images-amazon.com/images/I/41k8R%2Bn032L._BO2,204,203,200_PIsitb-sticker-arrow-click,TopRight,35,-76_AA300_SH20_OU01_.jpg",
type: "photo"
}
},
google: {
esp: [
{
label: "none",
score: 0.710983
},
{
label: "personal",
score: 0.113174
},
{
label: "social",
score: 0.091405
},
{
label: "environmental",
score: 0.084439
}
]
}
},
content_original: "Featuring analysis of healthcare issues and first-person stories, Policy & Politics in Nursing and Health Care helps you develop skills in influencing policy in today's changing health care environment. Approximately 150 expert contributors present a wide range of topics in policies and politics, providing a more complete background than can be found in any other policy textbook on the market. Discussions include the latest updates on conflict management, health economics, lobbying, the use of media, and working with communities for change. With these insights and strategies, you'll be prepared to play a leadership role in the four spheres in which ..."
}
Raw
Example3.bson
{
_id: ObjectId("534da53f78b7d47a18000002"),
bot_id: "52a9d052d2f6ac0d2b000000",
link: "http://www.simsimhe.com/bbs/?bo_table=humor&wr_id=1844058",
link_hash: "ca42a14b541d99b774c3bf1078610e02f7cb497e2a3a4c4fca22a284cc3a73e7",
source: "bing",
created: ISODate("2014-04-15T21:31:43.000Z"),
content: "할머니집에서 포켓몬 잡은 썰 .... ... 회원가입 아이디·비번 찾기 보안 할머니집에서 포켓몬 잡은 ...",
type: "page",
publisher: "simsimhe.com",
query: {
query: "(할머니 near:4 보안) AND loc:KR",
source: "bing"
},
meta: {
embedly: {
url: "http://www.simsimhe.com/bbs/?bo_table=humor&wr_id=1844058",
type: "html",
provider_name: "Simsimhe",
provider_url: "http://www.simsimhe.com",
provider_display: "www.simsimhe.com",
description: "할머니집에서 포켓몬 잡은 썰 ....",
title: "할머니집에서 포켓몬 잡은 썰 - 심심해닷컴 유머게시판"
},
alchemy: {
language: {
language: "korean",
"iso-639-1": "ko",
"iso-639-2": "kor",
"iso-639-3": "kor",
ethnologue: "http://www.ethnologue.com/show_language.asp?code=kor",
"native-speakers": "78 million",
wikipedia: "http://en.wikipedia.org/wiki/Korean_language"
}
}
}
}
Raw
Example4.json
{
_id: ObjectId("5331e63d99de704541000002"),
bot_id: "53318f29f2e22c962e000000",
link: "http://mrn-news.de/tag/stau/",
link_hash: "edb98b2e2b018a52a98638dedbba516d6f09aa4998a5c2e55e711f6bbfe1ed61",
source: "bing",
created: ISODate("2014-03-25T20:25:33.000Z"),
content: "Heidelberg / Bruchsal / Metropolregion Rhein-Neckar – Nachdem ein Verkehrsunfall auf der Autobahn A5 am Sonntagmorgen bereits ein Todesopfer gefordert hatte ...",
type: "page",
publisher: "mrn-news.de",
query: {
query: "(fahrspass near:4 durchschnitt) AND stau AND loc:DE",
source: "bing"
},
meta: {
embedly: {
url: "http://mrn-news.de/tag/stau/",
type: "html",
provider_name: "Mrn-news",
provider_url: "http://mrn-news.de",
provider_display: "mrn-news.de",
description: "Leimen / Rhein-Neckar-Kreis / Metropolregion Rhein-Neckar - Zu einem Frontalzusammenstoß, bei dem sich eine Fahrerin und ein Fahrer ...",
title: "Stau | - Metropolregion Rhein-Neckar News Metropolregion Rhein-Neckar News"
},
alchemy: {
language: {
language: "german",
"iso-639-1": "de",
"iso-639-2": "deu",
"iso-639-3": "deu",
ethnologue: "http://www.ethnologue.com/show_language.asp?code=deu",
"native-speakers": "105 million",
wikipedia: "http://en.wikipedia.org/wiki/German_language"
},
keywords: [
{
text: "de beteiligen",
relevance: "0.976962",
sentiment: {
type: "positive",
score: "0.249753"
}
},
{
text: "registrierung notwendig",
relevance: "0.868286",
sentiment: {
type: "positive",
score: "0.243903"
}
},
{
text: "mrn",
relevance: "0.743021",
sentiment: {
type: "positive",
score: "0.108627"
}
},
{
text: "partizipation",
relevance: "0.685803",
sentiment: {
type: "positive",
score: "0.200184"
}
}
],
sentiment: {
type: "positive",
score: "0.216253"
}
}
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment