RepLab 2014

RepLab is a competitive evaluation exercise for Online Reputation Management systems. In 2012 and 2013, RepLab focused on the problem of monitoring the reputation of (company) entities on Twitter, and dealt with the tasks of entity linking (“Is the tweet about the entity?”), reputation polarity (“Does the tweet have positive or negative implications for the entity’s reputation?”), topic detection (“What is the issue relative to the entity that is discussed in the tweet?”), and topic ranking (“Is the topic an alert that deserves immediate attention?”).

RepLab 2014 will again focus on Reputation Management on Twitter and will be addressing two new tasks, see below. We will use tweets in two languages: English and Spanish.

  1. The classification of tweets with respect to standard reputation dimensions such as Performance, Leadership, Innovation, etc.
  2. The classification of Twitter profiles (authors) with respect to a certain domain, classifying them as journalists, professionals, etc. Second, this task focuses on finding the opinion makers.

The second task is a part of the shared PAN-RepLab author profiling task. Besides the characterization of profiles from a reputation analysis perspective, participants can also attempt to classify authors by gender and age, which is the focus of PAN 2014.

Important dates:

  • March 1 – Training data released
  • March 17 – Test data released
  • May 5 – System results due

See http://nlp.uned.es/replab2014/ for more info and how to participate.

Overview of RepLab 2012: Evaluating Online Reputation Management Systems

This paper summarizes the goals, organization and results of the first RepLab competitive evaluation campaign for Online Reputation Management Systems (RepLab 2012). RepLab focused on the reputation of companies, and asked participant systems to annotate different types of information on tweets containing the names of several companies. Two tasks were proposed: a pro ling task, where tweets had to be annotated for relevance and polarity for reputation, and a monitoring task, where tweets had to be clustered thematically and clusters had to be ordered by priority (for reputation management purposes). The gold standard consisted of annotations made by reputation management experts, a feature which turns the RepLab 2012 test collection in a useful source not only to evaluate systems, but also to reach a better understanding of the notions of polarity and priority in the context of reputation management.

  • [PDF] E. Amigó, A. Corujo, J. Gonzalo, E. Meij, and M. de Rijke, “Overview of RepLab 2012: evaluating online reputation management systems,” in Clef (online working notes/labs/workshop), 2012.
    [Bibtex]
    @inproceedings{CLEF:2012:replab,
    Author = {Enrique Amig{\'o} and Adolfo Corujo and Julio Gonzalo and Edgar Meij and Maarten de Rijke},
    Booktitle = {CLEF (Online Working Notes/Labs/Workshop)},
    Date-Added = {2012-09-20 12:48:33 +0000},
    Date-Modified = {2012-10-30 09:30:49 +0000},
    Title = {Overview of {RepLab} 2012: Evaluating Online Reputation Management Systems},
    Year = {2012}}

Generating Pseudo Test Collections for Learning to Rank Scientific Articles

Pseudo test collections are automatically generated to provide training material for learning to rank methods. We propose a method for generating pseudo test collections in the domain of digital libraries, where data is relatively sparse, but comes with rich annotations. Our intuition is that documents are annotated to make them better findable for certain information needs. We use these annotations and the associated documents as a source for pairs of queries and relevant documents. We investigate how learning to rank performance varies when we use different methods for sampling annotations, and show how our pseudo test collection ranks systems compared to editorial topics with editorial judgements. Our results demonstrate that it is possible to train a learning to rank algorithm on generated pseudo judgments. In some cases, performance is on par with learning on manually obtained ground truth.

  • [PDF] R. Berendsen, M. Tsagkias, M. de Rijke, and E. Meij, “Generating pseudo test collections for learning to rank scientific articles,” in Information access evaluation. multilinguality, multimodality, and visual analytics – third international conference of the clef initiative, clef 2012, 2012.
    [Bibtex]
    @inproceedings{CLEF:2012:berendsen,
    Author = {Berendsen, Richard and Tsagkias, Manos and de Rijke, Maarten and Meij, Edgar},
    Booktitle = {Information Access Evaluation. Multilinguality, Multimodality, and Visual Analytics - Third International Conference of the CLEF Initiative, CLEF 2012},
    Date-Added = {2012-07-03 13:44:06 +0200},
    Date-Modified = {2012-10-30 08:37:52 +0000},
    Title = {Generating Pseudo Test Collections for Learning to Rank Scientific Articles},
    Year = {2012}}
Traditional Library Card Catalog

Conceptual language models for domain-specific retrieval

Over the years, various meta-languages have been used to manually enrich documents with conceptual knowledge of some kind. Examples include keyword assignment to citations or, more recently, tags to websites. In this paper we propose generative concept models as an extension to query modeling within the language modeling framework, which leverages these conceptual annotations to improve retrieval. By means of relevance feedback the original query is translated into a conceptual representation, which is subsequently used to update the query model.

Extensive experimental work on five test collections in two domains shows that our approach gives significant improvements in terms of recall, initial precision and mean average precision with respect to a baseline without relevance feedback. On one test collection, it is also able to outperform a text-based pseudo-relevance feedback approach based on relevance models. On the other test collections it performs similarly to relevance models. Overall, conceptual language models have the added advantage of offering query and browsing suggestions in the form of conceptual annotations. In addition, the internal structure of the meta-language can be exploited to add related terms.

Our contributions are threefold. First, an extensive study is conducted on how to effectively translate a textual query into a conceptual representation. Second, we propose a method for updating a textual query model using the concepts in conceptual representation. Finally, we provide an extensive analysis of when and how this conceptual feedback improves retrieval.

  • [PDF] [DOI] E. Meij, D. Trieschnigg, M. de Rijke, and W. Kraaij, “Conceptual language models for domain-specific retrieval,” Inf. process. manage., vol. 46, iss. 4, pp. 448-469, 2010.
    [Bibtex]
    @article{IPM:2010:Meij,
    Address = {Tarrytown, NY, USA},
    Author = {Meij, Edgar and Trieschnigg, Dolf and de Rijke, Maarten and Kraaij, Wessel},
    Date-Added = {2011-10-12 18:31:55 +0200},
    Date-Modified = {2011-10-12 18:31:55 +0200},
    Doi = {http://dx.doi.org/10.1016/j.ipm.2009.09.005},
    Issn = {0306-4573},
    Journal = {Inf. Process. Manage.},
    Number = {4},
    Pages = {448--469},
    Publisher = {Pergamon Press, Inc.},
    Title = {Conceptual language models for domain-specific retrieval},
    Volume = {46},
    Year = {2010},
    Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.ipm.2009.09.005}}
i found you!

A Semantic Perspective on Query Log Analysis

We present our views on the CLEF log file analysis task. We argue for a task definition that focuses on the semantic enrichment of query logs. In addition, we discuss how additional information about the context in which queries are being made could further our understanding of users’ information seeking and how to better facilitate this process.

  • [PDF] K. Hofmann, M. de Rijke, B. Huurnink, and E. Meij, “A semantic perspective on query log analysis,” in Working notes for the clef 2009 workshop, 2009.
    [Bibtex]
    @inproceedings{CLEF:2009:hofmann,
    Abstract = {We present our views on the CLEF log file analysis task. We argue for a task definition that focuses on the semantic enrichment of query logs. In addition, we discuss how additional information about the context in which queries are being made could further our understanding of users' information seeking and how to better facilitate this process. },
    Author = {Hofmann, K. and de Rijke, M. and Huurnink, B. and Meij, E.},
    Booktitle = {Working Notes for the CLEF 2009 Workshop},
    Date-Added = {2011-10-17 09:46:16 +0200},
    Date-Modified = {2011-10-17 09:46:16 +0200},
    Title = {A Semantic Perspective on Query Log Analysis},
    Year = {2009}}
Stack of books

Concept models for domain-specific search

We describe our participation in the 2008 CLEF Domain-specific track. We evaluate blind relevance feedback models and concept models on the CLEF domain-specific test collection. Applying relevance modeling techniques is found to have a positive effect on the 2008 topic set, in terms of mean average precision and precision@10. Applying concept models for blind relevance feedback, results in even bigger improvements over a query-likelihood baseline, in terms of mean average precision and early precision.

  • [PDF] E. Meij and M. de Rijke, “Concept models for domain-specific search,” in Evaluating systems for multilingual and multimodal information access, 9th workshop of the cross-language evaluation forum, clef 2008, aarhus, denmark, september 17-19, 2008, revised selected papers, 2009.
    [Bibtex]
    @inproceedings{CLEF:2008:meij,
    Author = {Meij, Edgar and de Rijke, Maarten},
    Booktitle = {Evaluating Systems for Multilingual and Multimodal Information Access, 9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008, Aarhus, Denmark, September 17-19, 2008, Revised Selected Papers},
    Date-Added = {2011-10-12 18:31:55 +0200},
    Date-Modified = {2012-10-30 08:44:35 +0000},
    Title = {Concept models for domain-specific search},
    Year = {2009}}
CLEF domain-specific sample graphic

The University of Amsterdam at the CLEF 2008 Domain Specific Track – Parsimonious Relevance and Concept Models

We describe our participation in the CLEF 2008 Domain Specific track. The research questions we address are threefold: (i) what are the effects of estimating and applying relevance models to the domain specific collection used at CLEF 2008, (ii) what are the results of parsimonizing these relevance models, and (iii) what are the results of applying concept models for blind relevance feedback? Parsimonization is a technique by which the term probabilities in a language model may be re-estimated based on a comparison with a reference model, making the resulting model more sparse and to the point. Concept models are term distributions over vocabulary terms, based on the language associated with concepts in a thesaurus or ontology and are estimated using the documents which are annotated with concepts. Concept models may be used for blind relevance feedback, by first translating a query to concepts and then back to query terms. We find that applying relevance models helps significantly for the current test collection, in terms of both mean average precision and early precision. Moreover, parsimonizing the relevance models helps mean average precision on title-only queries and early precision on title+narrative queries. Our concept models are able to significantly outperform a baseline query-likelihood run, both in terms of mean average precision and early precision on both title-only and title+narrative queries.

  • [PDF] E. Meij and M. de Rijke, “The University of Amsterdam at the CLEF 2008 Domain Specific Track – parsimonious relevance and concept models,” in Working notes for the clef 2008 workshop, 2008.
    [Bibtex]
    @inproceedings{CLEF-WN:2008:meij,
    Author = {Edgar Meij and Maarten de Rijke},
    Booktitle = {Working Notes for the CLEF 2008 Workshop},
    Date-Added = {2011-10-12 18:31:55 +0200},
    Date-Modified = {2012-10-30 09:28:58 +0000},
    Title = {The {U}niversity of {A}msterdam at the {CLEF} 2008 {Domain Specific Track} - Parsimonious Relevance and Concept Models},
    Year = {2008}}