CFP Web Mining and Content Analysis Track

Track chairs:

• Debora Donato (Ancestry, USA)
• Gerard de Melo (HPI/University of Potsdam, Germany)
• Qiaozhu Mei (University of Michigan, USA)

Contact:

We invite research contributions to the Web Mining and Content Analysis track at the 32nd edition of The Web Conference series (formerly known as WWW), to be held on April 30 - May 4, 2023, hosted by Austin, Texas, USA (/www2023/).

The Web Mining and Content Analysis track welcomes submissions of original and high-quality research papers related to the extraction of information from the Web, the analysis of the Web and social media content, recommendation of information on the Web, and mining of the Web usage data. We especially encourage submissions that propose novel and principled techniques or algorithms that can leverage the special characteristics of the Web, social media, and user behaviors for such extraction and mining. In addition to new techniques and algorithms, we also seek insights gained from the mining process.

The major focus of the Web Conference is to address the key challenges of Web-related scientific research. The general theme of the Web conference this year is “Web Research with Openness, Fairness and Reproducibility​​”. We particularly welcome submissions that align with this theme. Submissions that merely use one or another Web artifact — e.g., a dataset or a Web Application Programmer Interface (API) or a social network — rather than answering a specific Web-related scientific research challenge, are out of scope of the conference and will be rejected early during the reviewing process.

Please note that any submission for the track must make clear the relevance of the paper to the World Wide Web. Papers for which the relation to the World Wide Web is missing or unclear or implicit will be rejected. For instance, a paper on performance improvement of a general operating system would be out of scope even if it implicitly benefits Web servers, but if such a paper explicitly discusses and evaluates the effect of the proposed approaches on web servers then it would be in scope. Please also refer to the general relevance requirements as described in the general TheWebConf'23 Call for Papers.

Topics include (but are not limited to):

• Machine learning and data science for the Web

  • Learning representations and features from Web data
  • Machine learning algorithms for large-scale content mining
  • Web data integration and cleaning
  • Visualization of Web data
  • Robustness and generalizability of Web mining methods

• Language technologies and the Web

  • Human-machine dialogue on the Web
  • Community question answering
  • Fact-checking and detection of misinformation and disinformation
  • Normalization, clustering, classification, and summarization of Web text
  • Extraction of entities, attributes, relations, and events
  • Topic discovery and tracking
  • Sentiment analysis and opinion mining
  • Content-based information diffusion
  • Other forms of Web text and social media mining

• Integrating varied data

  • Mining multimedia and multimodal Web data
  • Mining multilingual and cross-lingual Web data
  • Bridging structured and unstructured data
  • Content and behavior data mining for Web 3.0

• Web activities and dynamics

  • Web traffic and log data analysis
  • Recommendation systems
  • Web measurements
  • Information diffusion on the Web (please also read the CFP of the “Social Networks and Graph Algorithms” track)
  • Models for Web evolution
  • Predictive analytics over Web datasets
  • Other novel Web mining applications

Authors should consult the conference’s main Research Track CFP to ensure their submissions are aligned with broader conference expectations, scope, and theme: “Web Research with Openness, Fairness and Reproducibility”. The CFP also details submission guidelines, relevant dates, and important policies.

Submissions that are out of scope or unresponsive to the call above will be rejected early during the reviewing process (“desk rejected”) with minimal feedback. For instance, a paper describing a Natural Language Processing method that is tested on a corpus obtained from a Website or API, but that does not address a research challenge of Web infrastructures, platforms, or ecosystems, would be considered out of scope for The Web Conference.

In case you have doubts whether your paper fits the scope of this track, please contact the track chairs: webmining-thewebconf2023@easychair.org