UNED at CLEf RepLab: Author Profiling
نویسندگان
چکیده
This paper describes a learning system developed for the RepLab 2014 author profiling task at UNED. The system uses a voting model, which employs a small set of features based mainly on the tweet text information such as POS tags, number of hashtags or number of links. In the unofficial run, the feature set was increased with Twitter metadata such as number of followers or retweet speed. The system achieved good results in author categorisation, although its performance in author ranking was low.
منابع مشابه
LIA@Replab 2014
In this paper, we present the participation of the Laboratoire Informatique d’Avignon (LIA) to RepLab 2014 edition [2]. RepLab is an evaluation campaign for Online Reputation Management Systems. LIA has produced an important number of experiments for every tasks of the campaign: Reputation Dimensions and both Author Categorization and Author Ranking sub-tasks from Author Profiling. Our approach...
متن کاملOverview of RepLab 2014: Author Profiling and Reputation Dimensions for Online Reputation Management
This paper describes the organisation and results of RepLab 2014, the third competitive evaluation campaign for Online Reputation Management systems. This year the focus lied on two new tasks: reputation dimensions classification and author profiling, which complement the aspects of reputation analysis studied in the previous campaigns. The participants were asked (1) to classify tweets applyin...
متن کاملUniversity of Tehran at RepLab 2014
In this paper, we present our approach to author ranking subtask; which is a part of author-profiling task in RepLab 2014. In this subtask, systems are expected to detect influential authors and opinion makers on Twitter website. The systems’ output, for a given domain, must be a ranked list of authors according to their probability of being an influential author or opinion maker. Our system ut...
متن کاملUNED-READERS: Filtering Relevant Tweets using Probabilistic Signature Models
This paper describes the (usupervised) knowledge-based approach to filter relevant tweets for a given entity that is followed by the UNED-READERS system at RepLab 2013. The approach relies on a new way of contextualizing entity names from relative large and broad collections of texts using probabilistic signature models (i.e., discrete probability distributions of words lexically related to the...
متن کاملUNED at RepLab 2012: Monitoring Task
This paper describes the UNED participation at RepLab 2012 Monitoring Task. Given an entity and a tweet stream containing the entity’s name, the task consists on grouping the tweets in topics and then ranking the identified topics by priority. We tested three different systems to deal with the clustering problem: (i) an agglomerative clustering based on term co-occurrences, (ii) a clustering me...
متن کامل