Named Entity Recognition and Disambiguation (NERD) systems are foundational for information retrieval, question answering, event detection, and other natural language processing (NLP) applications. We introduce TweetNERD, a dataset of 340K+ Tweets across 2010-2021, for benchmarking NERD systems on Tweets. This is the largest and most temporally diverse open sourced dataset benchmark for NERD on Tweets and can be used to facilitate research in this area. We describe evaluation setup with TweetNERD for three NERD tasks: Named Entity Recognition (NER), Entity Linking with True Spans (EL), and End to End Entity Linking (End2End); and provide performance of existing publicly available methods on specific TweetNERD splits. TweetNERD is available at: https://doi.org/10.5281/zenodo.6617192 under Creative Commons Attribution 4.0 International (CC BY 4.0) license. Check out more details at https://github.com/twitter-research/TweetNERD.

The worldwide adoption of Twitter turned it into one of the most popular platforms for content analysis as it serves as a gauge of the public’s feeling and opinion on a variety of topics. This is particularly true of political discussions and lawmakers’ actions and initiatives. Yet, one common but unrealistic assumption is that the data of interest for analysis is readily available in a comprehensive and accurate form. Data need to be retrieved, but due to the brevity and noisy nature of Twitter content, it is difficult to formulate user queries that match relevant posts that use different terminology without introducing a considerable volume of unwanted content. This problem is aggravated when the analysis must contemplate multiple and related topics of interest, for which comments are being concurrently posted. This article presents Active Tweet Retrieval Visualization (ATR-Vis), a user-driven visual approach for the retrieval of Twitter content applicable to this scenario. The method proposes a set of active retrieval strategies to involve an analyst in such a way that a major improvement in retrieval coverage and precision is attained with minimal user effort. ATR-Vis enables non-technical users to benefit from the aforementioned active learning strategies by providing visual aids to facilitate the requested supervision. This supports the exploration of the space of potentially relevant tweets, and affords a better understanding of the retrieval results. We evaluate our approach in scenarios in which the task is to retrieve tweets related to multiple parliamentary debates within a specific time span. We collected two Twitter datasets, one associated with debates in the Canadian House of Commons during a particular week in May 2014, and another associated with debates in the Brazilian Federal Senate during a selected week in May 2015. The two use cases illustrate the effectiveness of ATR-Vis for the retrieval of relevant tweets, while quantitative results show that our approach achieves high retrieval quality with a modest amount of supervision. Finally, we evaluated our tool with three external users who perform searching in social media as part of their professional work.

Twitter has become one of the most important platforms for gathering information, where users follow breaking news, track ongoing events and learn about their topics of interest. Considering the sheer volume of Twitter data and the ever-growing number of users, it is of great importance to have real-time systems that can monitor and recommend relevant and non-redundant tweets with respect to users' interests. In this paper, we propose a framework using language models as a basis for analyzing strategies and techniques for tweet recommendation based on user interest profiles. Results show that identifying named entities in profiles has a major impact on the accuracy of the recommender. We also performed a thorough comparison to investigate whether state-of-the-art semantic relatedness techniques have a positive impact on the precision of the recommended tweets. The TREC 2015 Microblog track dataset is used for comparison and evaluation throughout this paper.

Users of microblogging social networks produce millions of short messages every day. Retrieving relevant information to a particular event from this sheer volume of data is not a trivial task. In this paper, we present a framework for the retrieval of Twitter posts that are relevant to a set of political debates. Our main contribution is the proposal of a set of strategies for involving the user in the retrieval process, so that by presenting to her meaningful posts to be labeled, the method achieves a noticeably higher accuracy. The correct retrieval or labeling could be provided by an external information source such as a domain expert, or simulated with an oracle. A key aspect of active retrieval methods is to request the labels of the instances that help improve the retrieval accuracy the most, while keeping the number of labeling requests to a minimum. The proposed strategies for selecting labeling requests make use of the textual content of tweets and their structural information. The experimental results show the advantages of the proposed methods and the effectiveness of the selection strategies for involving the user in the retrieval process.