Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Deep Text Mining of Instagram Data Without Strong Supervision
KTH.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Programvaruteknik och datorsystem, SCS.ORCID-id: 0000-0002-7786-9551
KTH.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Programvaruteknik och datorsystem, SCS.ORCID-id: 0000-0002-4722-0823
2018 (engelsk)Inngår i: Proceedings - 2018 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2018, IEEE, 2018, s. 158-165Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

With the advent of social media, our online feeds increasingly consist of short, informal, and unstructured text. This textual data can be analyzed for the purpose of improving user recommendations and detecting trends. Instagram is one of the largest social media platforms, containing both text and images. However, most of the prior research on text processing in social media is focused on analyzing Twitter data, and little attention has been paid to text mining of Instagram data. Moreover, many text mining methods rely on annotated training data, which in practice is both difficult and expensive to obtain. In this paper, we present methods for unsupervised mining of fashion attributes from Instagram text, which can enable a new kind of user recommendation in the fashion domain. In this context, we analyze a corpora of Instagram posts from the fashion domain, introduce a system for extracting fashion attributes from Instagram, and train a deep clothing classifier with weak supervision to classify Instagram posts based on the associated text. With our experiments, we confirm that word embeddings are a useful asset for information extraction. Experimental results show that information extraction using word embeddings outperforms a baseline that uses Levenshtein distance. The results also show the benefit of combining weak supervision signals using generative models instead of majority voting. Using weak supervision and generative modeling, an F1 score of 0.61 is achieved on the task of classifying the image contents of Instagram posts based solely on the associated text, which is on level with human performance. Finally, our empirical study provides one of the few available studies on Instagram text and shows that the text is noisy, that the text distribution exhibits the long-tail phenomenon, and that comment sections on Instagram are multi-lingual.

sted, utgiver, år, opplag, sider
IEEE, 2018. s. 158-165
Emneord [en]
Information extraction, Instagram, Weak Supervision, Word Embeddings
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-245979DOI: 10.1109/WI.2018.00-94ISI: 000458968200021Scopus ID: 2-s2.0-85061892408ISBN: 9781538673256 (tryckt)OAI: oai:DiVA.org:kth-245979DiVA, id: diva2:1295887
Konferanse
18th IEEE/WIC/ACM International Conference on Web Intelligence, WI 2018; Santiago; Chile; 3 December 2018 through 6 December 2018
Merknad

QC 20190313

Tilgjengelig fra: 2019-03-13 Laget: 2019-03-13 Sist oppdatert: 2019-03-13bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Jaradat, ShathaMatskin, Mihhail

Søk i DiVA

Av forfatter/redaktør
Hammar, KimJaradat, ShathaDokoohaki, NimaMatskin, Mihhail
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 84 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf