Real-time monitoring of sentiment in business related Wikipedia

From Brede Wiki
Jump to: navigation, search
Conference paper (help)
Real-time monitoring of sentiment in business related Wikipedia
Authors: Finn Årup Nielsen, Michael Etter, Lars Kai Hansen
Citation: missing booktitle  : 2013
Editors:
Publisher: Define publisher
Meeting: Define meeting
Database(s):
DOI: Define doi.
Link(s): http://www2.imm.dtu.dk/pubdb/views/edoc_download.php/6545/pdf/imm6545.pdf
Search
Web: DuckDuckGo Bing Google Yahoo!Google PDF
Article: Google Scholar PubMed
Restricted: DTU Digital Library
Services
Format: BibTeX

Real-time monitoring of sentiment in business related Wikipedia describes an online system with sentiment analysis of business-related Wikipedia articles

The system monitors the IRC stream from Wikimedia and detects changes on English Wikipedia article related to specific companies. With a word list-based approach using the AFINN sentiment-annotated word list each change and revision is scored for sentiment.

The system is related to the "Wikiganda" system that was described in a student work.[1] and the manual content analysis study by Marcia W. DiStaso and Marcus Messner.[2]

A network visualization inspired by Iba et al.[3] and Keegan et al.[4] is used to display the editor dynamics.

The paper is submitted to a conference.

Contents

[edit] Wikimedia Research Newsletter summary

By Dario Taraborelli, Piotr Konieczny, Oren Bochman, Taha Yasseri, Jonathan T. Morgan and Tilman Bayer. See original at [1].

[edit] Too good to be true? Detecting COI, Attacks and Neutrality using Sentiment Analysis

Finn Årup Nielsen, Michael Etter and Lars Kai Hansen presented a technical report[1] on an online service which they created to conduct real-time monitoring of Wikipedia articles of companies. It performs sentiment analysis of edits, filtered by companies and editors. Sentiment analysis is a new applied linguistics technology which is being used in a number of tasks ranging from author profiling to detecting fake reviews on online retailers. The form of visualization provided by this tool can easily detect deviation from linguistic neutrality. However, as the authors point out, this analysis only gives a robust picture when used statistically and is more prone to mistakes when operating within a limited scope.

The service monitors recent changes using an IRC stream and detects company-related articles from a small hand-built list. It then retrieves the current version using the MediaWiki API and performs sentiment analysis using the AFINN sentiment-annotated word list. The project was developed by integrating a number of open source components such as NLTK and CouchDB. Unfortunately, the source code has not been made available and the service can only run queries on the shortlisted companies which will limit the impact of this report on future Wikipedia research. However, it seems to have potential as a tool for detecting COI edits that tend to tip neutrality by adding excess praise or attacks which tip the content in the other direction. We hope the researchers will open-source this tool like their prior work on the AFINN data-set, or at least provide some UI to query articles not included in the original research.

[edit] Related papers

  1. Early prediction of movie box office success based on Wikipedia activity big data
  2. Extracting event-related information from article updates in Wikipedia
  3. Informed investors and the Internet
  4. Quantifying Wikipedia usage patterns before stock market moves
  5. Temporal summarization of event-related updates in Wikipedia

[edit] References

  1. Wikiganda: identifying propaganda through text analysis
  2. Forced transparency: corporate image on Wikipedia and what it means for public relations
  3. Analyzing the creative editing behavior of Wikipedia editors: through dynamic social network analysis
  4. Staying in the loop: structure and dynamics of Wikipedia's breaking news collaborations
Personal tools