Draft:Gavagai Explorer

From Wikipedia, the free encyclopedia
  (Redirected from Draft:Gavagai AB)
Jump to navigation Jump to search
  • Symbol opinion vote.svg Comment: Still fails WP:NCORP due to lack of independent secondary sources talking about the company. Probably fails WP:G11. -- RoySmith (talk) 21:56, 4 June 2019 (UTC)
  • Symbol opinion vote.svg Comment: Thank you for including references in your submission. Please help our volunteer reviewers by identifying, on the draft's talk page, the WP:THREE best sources that establish notability of the subject. ~Kvng (talk) 15:38, 26 May 2019 (UTC)
  • Symbol opinion vote.svg Comment: Issues are non independent sources (interview ones), routine sources (award announcements), or sources when taken together don't show WP:SIGCOV, please read WP:SIGCOV and WP:NCORP to see what sources are needed. JC7V (talk) 19:00, 8 December 2018 (UTC)
  • Symbol opinion vote.svg Comment: Simply still not enough in-depth third-party sources overall. SwisterTwister talk 04:42, 26 December 2015 (UTC)
  • Symbol opinion vote.svg Comment: Wikipedia articles about companies require strong referencing in order to be suitable for inclusion. However, this draft does not yet provide acceptable references, as all the sources are from sites related to Gavagai. We need references about the company, not by them, in order to show notability. To that end, please find and add a variety of reliable, independent (third-party) sources that discuss the subject in significant detail. Thanks, /wia /tlk 16:09, 5 December 2015 (UTC)

Several of the sources now (refs 8 to 16 as per the current version of the page) are not interviews nor award announcements but actual news reports on results and analyses generated by the company. I am not entirely comfortable editing the page too much since I am involved with the company myself, but I did try now to break up the paragraph a bit to make the relative status of the references clearer! (I also added a recent Ph D thesis entirely independent of the company as a reference (reference number 7)). Jussi Karlgren (talk) 08:14, 20 February 2019 (UTC)

Gavagai Explorer
Developer(s)Gavagai AB
Operating systemSaaS
Available in45 languages
TypeText analytics

Gavagai Explorer is a text analytics tool developed by Gavagai used to process unstructured text data such as answers to open-ended questionnaires, comments, customer reviews, online mentions, customer feedback interactively by non-technical analysts. Gavagai Explorer is delivered as SaaS and is designed for professional but non-technical users, primarily to be used by market researchers, PR agencies, opinion analysts, academic researchers and in-house customer relationship management teams at large and small corporations and government agencies in a large number of sectors and fields in many linguistic and cultural areas.

Technical features[edit]

Gavagai Explorer clusters sentences from input texts in numerous languages automatically by topical themes and then scores them by tonality by a default 8-dimensional sentiment palette (general positive, general negative, love, hate, desire, fear, violence, skepticism) or by sentiment poles tailored for the task at hand.[1] and allows the analyst to work with the quality of the clusters by interactively merging or discarding proposed clusters, and by inspecting the terms selected by the system as clustering criteria to refine the set.[2] Unlike many other text clustering systems, Gavagai Explorer relies on term occurrence as a primary clustering criterion, instead of inferring a latent topic model. This is motivated by the desire of the designers to improve the transparency of the resulting analysis and the accessibility of the clustering criteria for human analysts: using words and multi-word terms explicitly mentioned in the text allows the analyst to immediately understand why e.g. a text is miscategorised and then adjust the cluster terms to reflect that error. Suggestions for terms to be included for improving cluster coverage are generated by consulting a back-end dictionary built by learning semantic relations from continuous monitoring of general language usage. Using latent (non-observable) variables instead may allow for greater precision but at a cost to editability and transparency.


Gavagai Explorer builds on a back-end originally developed as a research project[3][4] by Jussi Karlgren and Magnus Sahlgren, founders of the text analytics company Gavagai. Gavagai was formed in 2007[5] to commercialise previous research by the founders on distributional semantics. Gavagai Explorer was originally developed to demonstrate the versatility of the approach to learning semantic relationships from text which is uniquely implemented as a form of the random indexing.[3] The resulting learning lexicon was made available through a developer API but the interest for the demonstration tool was greater than the back end which today is the most important product for the company.[6] Today Gavagai Explorer is used by market research companies and by academic researchers alike.[7]

The back end technology has been used for media monitoring e.g. for public event outcome prediction such as predicting the winner of the Eurovision Song Contest,[8][9] and for the analysis of political discourse.[10][11][12][13][14] Recently (2018), the distributional semantics procedure has been applied to recordings of dolphin vocalisation.[15][16] Gavagai has received numerous prizes[17][18] and media attention for its technology approach and research background.[19]


  1. ^ Karlgren, Jussi; Sahlgren, Magnus; Olsson, Fredrik; Espinoza, Fredrik; Hamfors, Ola (2012). "Usefulness of Sentiment Analysis". Proceedings of the 34th European Conference on Advances in Information Retrieval (ECIR'12). Barcelona, Spain: Springer Verlag. pp. 426–435. doi:10.1007/978-3-642-28997-2_36. ISBN 978-3-642-28996-5.
  2. ^ Espinoza, Fredrik; Hamfors, Ola; Karlgren, Jussi; Olsson, Fredrik; Persson, Per; Hamberg, Lars; Sahlgren, Magnus (March 2018). "Analysis of Open Answers to Survey Questions through Interactive Clustering and Theme Extraction". Proceedings of the 2018 Conference on Human Information Interaction & Retrieval. New Brunswick, NJ, USA: ACM. pp. 317–320. doi:10.1145/3176349.3176892. ISBN 978-1-4503-4925-3.
  3. ^ a b Sahlgren, Magnus; Cuba Gyllensten, Amaru; Espinoza, Fredrik; Hamfors, Ola; Karlgren, Jussi; Olsson, Fredrik; Persson, Per; Viswanathan, Akshay; Holst, Anders (May 2016). "The Gavagai Living Lexicon" (PDF). Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). Portorož, Slovenia: European Language Resources Association (ELRA). ISBN 978-2-9517408-9-1.
  4. ^ Sahlgren, Magnus; Karlgren, Jussi (2009). "Terminology Mining in Social Media". Proceedings of the 18th ACM Conference on Information and Knowledge Management (CIKM '09). Hong Kong, China: ACM. pp. 405–414. doi:10.1145/1645953.1646006. ISBN 978-1-60558-512-3.
  5. ^ Lewan, Mats (16 April 2013). "Gavagai: Lär sig ett språk på några timmar". NyTeknik. Retrieved 21 December 2015.
  6. ^ "Gavagai | CrunchBase". CrunchBase. Retrieved 21 November 2018.
  7. ^ Georg, Carina (2019). Virtual patients in nursing education : teaching, learning and assessing clinical reasoning skills. Solna, Sweden: Karolinska Institutet. ISBN 978-91-7831-289-4.
  8. ^ Wilhelmson, Annika (2012-03-09). "Så snackar vi schlager på nätet (This Is How We Talk About Pop On The Web)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  9. ^ Neuman, Ricki; Hellekant, Johan (2012-05-26). "Sveriges bidrag en global snackis (The Swedish Entry Creates Global Buzz)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  10. ^ Sjöholm, Gustav (2011-10-28). "Datorer kan förutspå framtida revolutioner (Computers can predict future revolutions)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  11. ^ Brandel, Tobias (2013-01-18). "Makthavare på en retorisk resa (Politicians Make Rhetorical Journey)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  12. ^ Brandel, Tobias (2013-01-18). "Ordens vandring i politiken (How Words Drift In Politics)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  13. ^ Brandel, Tobias (2013-01-23). "Personligt tilltal politiskt rätt (Personal Touch Is Politically Appropriate)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  14. ^ Gudmundson, Per (2014-04-09). "Politik är mindre än vi tror (Politics are less important than we may believe)". Svenska Dagbladet (in Swedish). Retrieved 2018-11-23.
  15. ^ NatureWorldNews (2017-05-02). "Dolphin Language Could Be Translated Using Artificial Intelligence By 2021". Nature World News. Retrieved 2018-08-24.
  16. ^ "Bloomberg: Swedish Startup Uses AI to Figure Out What Dolphins Talk About". Retrieved 2018-10-15.
  17. ^ "Stockholm Chamber of Commerce - AI-Company Gavagai receives entrepreneur prize from Stockholm Chamber of Commerce and Swedish Lunch in Davos". english.chamber.se. Retrieved 2018-08-24.
  18. ^ "Alla tidigare vinnare". Ny Teknik (in Swedish). Retrieved 2018-08-24.
  19. ^ Norden, Alex (2011-12-13). "Finding meaning before it is evident to revolutionize real-time trend analysis". Scandinavian Startups News. Retrieved 2018-11-23.

External links[edit]