This classifier determines if a text is positive or negative. It is well suited for both short and long texts (tweets, Facebook statuses, blog posts, product reviews etc). It’s trained on 2.8 million documents with data from Twitter, Amazon product reviews and movie reviews. It can be used to conduct research, brand surveys and see trends around market campaigns. You may access the sentiment analysis api by signing up (free)! Read more about the classifier in at blog.uclassify.com/sentiment-analysis-api
by uClassifyThis classifier tries to figure out if a text is written by a male or female. It has been trained on 11000 blogs (5500 blogs written by females and 5500 by males). More text gives better results.
by uClassifyCategories an English text into a topic (Arts, Business, Computers, Games, Health, Home, Recreation, Science, Society and Sports). Each of those topics has more specific child classifier (Art Topics, Business Topics etc). It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassify
We recommend using our new better classifier called 'Language Detector' instead. Classifies the language of a text by looking on about 4000 commonly used words per language. It works best with clean texts but can also be used for HTML pages. For reliable results HTML pages need more text content (since HTML often contains English words and comments).
by uClassify
The IAB Taxonomy classifier categories texts into one of 360 topics. It has two levels of depth, a main category (e.g. sports, business or science) and subcategories (soccer, agriculture or physics). It's based on the IAB Quality Assurance Guidelines (QAG) Taxonomy. The class name has 4 parts, separated by underscores: "main topic_sub topic_id1_id2" where the ids are the IAB level 1 and 2 ids.
by uClassifyThis classifier tries to estimate to which age group a blog belongs. The training data is based upon about 7000 blogs collected randomly from Internet.
by uClassifyThe IAB Taxonomy V2 classifier categories texts into 560 topics. It has four levels of depth, a main category (e.g. sports, business or science) and subcategories (soccer, agriculture or physics). It's based on the IAB Quality Assurance Guidelines (QAG) Content Taxonomy V2, released 1 March 2017. The class name has up to 6 parts, separated by underscores: "main topic_sub topic_id1_id2_id3_id4" where the ids are the IAB level ids (use the ids for mapping).
by uClassifyThe state of mind of the writer - upset or happy. On the extreme side there is angry, hateful writers and ton the other extreme there is joyful and loving writers. The measured accuracy is 96% (using 10-fold cross validation). For reliable results we recommend that you use at least 200 words.
by prfektAnalyzes the Extraversion/Introversion dimension of the personality type according to Myers-Briggs personality model. The analysis is based on the writing style and should NOT be confused with the MBTI (c) which determines personality type based on self-assessment questionnaires. Training texts are manually selected from mainly blog posts based on the authors understanding of personality and writing style (see Jensen & DiTiberio, 1989).
by prfektDetermines the Thinking/Feeling dimension of the personality type according to Myers-Briggs personality model. The analysis is based on the writing style and should NOT be confused with the MBTI (c) which determines personality type based on self-assessment questionnaires. Training texts are manually selected mainly from blog posts based on the authors understanding of personality and writing style (see Jensen & DiTiberio, 1989).
by prfektDetermines the Judging/Perceiving dimension of the personality type according to Myers-Briggs personality model. The analysis is based on the writing style and should NOT be confused with the MBTI (c) which determines personality type based on self-assessment questionnaires. Training texts are manually selected mainly from blog posts based on the authors understanding of personality and writing style (see Jensen & DiTiberio, 1989).
by prfektDetermines the Sensing/iNtuition dimension of the personality type according to Myers-Briggs personality model. The analysis is based on the writing style and should NOT be confused with the MBTI (c) which determines personality type based on self-assessment questionnaires. Training texts are manually selected mainly from blog posts based on the authors understanding of personality and writing style (see Jensen & DiTiberio, 1989).
by prfektDetermines the tonality of a text - corporate (formal) or personal (informal). Helps distinguish between prosumer media and pro media for instance.
by prfektCategories an English text into a computer topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into a society topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into a sport topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into an art topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into an business topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassify
This classifier identifies the language of a text. It can detect more than 370 major and rare languages; living (e.g. English, Chinese), constructed (e.g. Klingon, Esperanto), ancient and extinct. At least a few words are needed to get accurate results. The language name is appended with an underscore followed by its ISO 639-3 code. The text is expected to be UTF-8 encoded, also keep in mind that more languages may be added.
by uClassifyCategories an English text into a recreation topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into a home topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassify
Latvian sentiment classifier. Trained on food tweet data from www.twitediens.ml
by saiferCategories an English text into a health topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into a science topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassifyCategories an English text into a game topic. Use the parent classifier 'Topics' to find out if a text belongs in this category. It uses a subset of topics from the Open Directory Project at http://www.dmoz.org.
by uClassify
This classifier has been trained on 21 different classical authors. We have used about three books per author collected from the Gutenberg project. It only works for English texts. Try it out to see which poet your blog or text is most alike!
by uClassify
This classifier categorizes news articles. It was trained with 1000 hand picked articles from major news sources per category. The text used was a combination of each article's title, description and scraped and cleaned text.
by mvazquez
Classification between Semantic/pragmatic puns and phonological puns
by aangtceTries to determine the values (i.e. worldview) expressed by the author according to Clare W. "Graves Emergent Cyclic Levels of Existence Theory".
by prfekt
by arturgorczynski
by virus32
Tries to determine whether a text was written by someone who is liberal or conservative in ideology.
by Politimind
Analyzes the cognitive functions used for a text according to the Myers-Briggs Personality Theory. A database with more than 20 thousand words combining the slang words, words and phrase constructions most used by each type of personality, obtained in forums and controlled blogs. Please keep in mind that this test does not serve as an MBTI personality test, most people fluctuate between two or more types depending on the situation or subject, people can change mental state, for example, an INTP personality type talking about the past can be typed as a type of personality that uses the cognitive function Si, since this test only evaluates the functions used in the text. In order to get an idea of what an individual's personality is, it is advisable to gather a considerable amount of text (500 to 1000 words for a decent analysis - 9000 for perfect) written by that person in order to discover their most used functions. Usually, you'd get a better result if you get the person to answer an open-ended question where they express an opinion. Constantly updating for more accurate results. Enjoy! (Note: It only works well with native English speaking people)
by g4mes543
Web Categories
by ephraimalbaro
Canadian government publication category classifier. categories map = { "Agriculture, environment, fisheries and natural resources": "agriculture_environment", "Arts, culture and entertainment": "arts_culture", "Business, industry and trade": "business_industry", "Economics and finance": "economics_finance", "Education, language and training": "education_language", "Employment and labour": "employment_labour", "Government, Parliament and politics": "government_politics", "Health and safety": "health_safety", "Indigenous affairs": "indigenous_affairs", "Information and communications": "information_communications", "International affairs and defence": "international_affairs", "Law, justice and rights": "law_justice", "Science and technology": "science_technology", "Social affairs and population": "social_affairs", }
by Frederick
Direction of focus - introversion/inner world (AQAL: UL + LR) or extraversion/outer world (AQAL: LL + UR). I believe this also shows wether a person is inner directed and thus prioritize other people´s opinions and experiences over one´s own (extravert) or outer directed (introvert). The class "extraversion" has been trained on 130455 features (words) whereof 24576 are unique.The class "introversion" has been trained on 83764 features (words) whereof 18111 are unique.
by prfekt
Language style abstract (big words) or concrete (facts and details). AQAL: UR + UR vs LL + LR. The class "abstract" has been trained on 110178 features (words) whereof 22070 are unique. The class "concrete" has been trained on 104040 features (words) whereof 20693 are unique.
by prfekt
by amnorvend
Tries to guess whether a statement is true or false.
by Politimind
IAB Level One Classification with a Denver, Colorado twist. UPPER CASE text only, please.
by scox1000
by umesh_menon13
by casper
Determines the perspective (i.e. quadrant) expressed by the author according to Ken Wilber's Integral Theory (AQAL - all quadrants all levels).
by prfekt
Discourse denotes written and spoken communications, it can classify phrases into questions, answers or more fine grained categories such as agreement, disagreement, elaboration etc. It works best with short texts such as tweets. For longer texts consider splitting it into sentences or phrases on beforehand. It's based on the dataset from the paper "Characterizing Online Discussion Using Coarse Discourse Sequences (ICWSM '17)"
by uClassify
Eggo
by boattyman
This news categorizer is only a simple example used in a tutorial. It has been trained on 20 texts per category (sports, entertainment and science) so don't expect too much (even though it seems to do incredibly well).
by uClassify
by ranez
This is a classifier for identifying web page contents.....
by cbaproject076
The monkeys playing on the airplane, together move to an island far away. They come from and to where?
by Chickyky
by someperson101
Mood Tracker is used best on individual blog posts, tweets, etc. which are then compared to other posts thus tracking the authors mood for that period!
by becky411
by FunctionXu
by Willothy
kvista's librarything classifier
by kvista
What parts of reality the author chooses to focus on. AQAL: quadrants. The class "Personal UL" has been trained on 27202 features (words) whereof 7384 are unique. The class "Philosophical LR" has been trained on 56561 features (words) whereof 13686 are unique. The class "Practical UR" has been trained on 76606 features (words) whereof 16798 are unique. The class "Social LL" has been trained on 53617 features (words) whereof 12721 are unique.
by prfekt
Interest in people (subjective) or things (objective). AQAL: UL + LL vs UR + LR. The class "people" has been trained on 80819 features (words) whereof 16949 are unique. The class "things" has totaly been trained on 133399 features (words) whereof 25393 are unique.
by prfekt
by fabfre
Classifies text into Symptoms, Cure and Diseases
by Talha
by DullDemoon3
Focusing purely on core or motivational drives of the person from each individual type alone, erasing any bit of archetypes or typically perceived common traits possible. Seeking a true objective enneagram type. Keep in mind, depending on the situation, subject matter, state of mind, emotion results could differ so keep it considerable and clear with around 2000+ for best accuracy usually open-ended, Biography, opinions, or something similar. (Disclaimer: This is not an enneagram test and don't define but a possibility analyzes enneagram and wing in order, updates time from time for better results and this shouldn't correlate or reconsider MBTI or any alternative type system) --- Examples of a few common stereotypes or traits being cut. 1: Ideal, logical, cold, strict, organized 2: Sociable, friendly, emotional, pleaser 3: Extroverted, charming, sociable, arrogant 4: emotional, introvert, creative, artistic, different 5: logical, intelligent, introvert, abstract, withdrawn 6: loyal, anxious, conventional, defenceless 7: Spontaneous, extrovert, adventurous carefree 8: Demanding, cold, controlling, extrovert 9: Passive, lazy, friendly, defenceless ---- Clarity of cores 1: Want to be internally moral, search the best option 2: Want to be loved, search criteria to be cared for 3: Want significance, special and importance 4: Want an identity/destiny to be satisfied with 5: Wants to be prepared for the environment’s criteria 6: Want clear direction, moment stability 7: Want comfort escape prolong suffering 8: Wants security of maintaining their life in control 9: Wants self/external peace with things kept
by ohubobubo
by P
Okay, this classifier is still harboring much room for improvement. It's been trained on words across various astrology blogs. I hope you'll at least find it somewhat enjoyable!
by DullDemoon3
by scox1000
by angakokpanipaq
there are three types of websites in the world.
by bethglass
by BrickleRex
To tell the difference between Apple the Fruit and Apple Computer
by rcheramy
A classifier based on the Runic poetry and the poetic meaning of the Runes, rather than the modern-day interpretations.
by damir666
by multisystem
by khodrog
by Nelson
Classifies music into Rock or Pop based on lyrics. A few hundies of lyrics were used to train classifier. Ovaj klasifikator ce razvrstati muziku po žanrovima na osnovu teksta. Uspešnost zagarantovana!
by fon
by Danielmagox
by 17pmg
by balkis
by Mansour Omar Almenhali
This classifier will try to predict if a movie passes or fails the Bechdel Test by looking at the plot and/or subtitles of a movie. It's is trained with about 6000 IMDB plots and 2400 movie subtitles that has failed and passed the Bechdel Test according to bechdeltest.com.
by uClassify
by DullDemoon3
by achintyagi
test classifier
by eric234
by virus32
Krakin't Research and Development classifier. Please use this classifier to evaluate ideas and whether they are suitable for the Krakin't project. This way, no text will be collected, and no ideas stolen.
by krakint
by gunawan01
by pgaldamez
Detects if a script is a Roblox virus or not.
by Aon
Classifies Hindustani Raags based on input. Input must be in the form of single-character Swars. EG: s R r G g m M p D d N n All Komal or Teevra Swars are capitalized. Input example: srg pds sdp grs Important: The Swars should be grouped in three-characters.
by Soham Korade
This classifier is a test to see if background information can be distinguished from recommendations.
by wmp0
Classifier for sports news stories with intelligence specific to Denver, CO. Uppercase text only.
by scox1000
by gunawan01
by renjithpta
by mesadhan
danganronpa v3 characters! trained w quotes, a wip
by junko
Monalisa Text classifier
by jairribeiro1
by arturgorczynski
It's only for russian texts! This classifier specifies whether the text is a work of science fiction or not. (Roger Zelazny detected with unstable results, for obvious reasons.) And of course the Russian text in the description of the classifier is not supported by uClassify...
by Shadowmaster
This classifier currently outputs 2 categories..
by achintyagi
This is a Test Classifier.
by Srikanth Tanniru
by ssdupree
Bu metin siniflandirma filtresi bilgisayar algoritmalari kullanarak bir yazinin hangi yazar tarafindan yazildigini tahmin etmeye çalisir. Sistem su an beta asamada ve ilk etapata kayitli 4 yazar var: Ahmet Turan Alkan,Cüneyt Özdemir, Cengiz Çandar ve Ezgi Basaran. Bu yazarlardan birinin yazisindan birkaç paragrafi kopyalayip asagidaki metin kutusuna yapistirin, uClassfiy! tusuna basinca sistem size yazinin hangi yazara ait olduguyla ilgili tahminini sunacak. Hüseyin Demirtas, boun, cogsci huseyindemirtas.net
by dilsayar
by kaihv87
by achintyagi
by RAOUYA AAMIR
by PColinot
by surajsharma
Typical info.nl topics
by oebe