The recent advances in natural language processing have yielded many exciting developments in text analysis and language understanding models; however, these models can also be used to track people, bringing severe privacy concerns. In this work, we investigate what individuals can do to avoid being detected by those models while using social media platforms. We ground our investigation in two exposure-risky tasks, stance detection and geotagging. We explore a variety of simple techniques for modifying text, such as inserting typos in salient words, paraphrasing, and adding dummy social media posts. Our experiments show that the performance of BERT-based models fine-tuned for stance detection decreases significantly due to typos, but it is not affected by paraphrasing. Moreover, we find that typos have minimal impact on state-of-the-art geotagging models due to their increased reliance on social networks; however, we show that users can deceive those models by interacting with different users, reducing their performance by almost 50%.

The high cost of constructing test collections led many researchers to develop intelligent document selection methods to find relevant documents with fewer judgments than the standard pooling method requires. In this paper, we conduct a comprehensive set of experiments to evaluate six bandit-based document selection methods, in terms of evaluation reliability, fairness, and reusability of the resultant test collections. In our experiments, the best performing method varies across test collections, showing the importance of using diverse test collections for an accurate performance analysis. Our experiments with six test collections also show that Move-To-Front is the most robust method among the ones we investigate.

The scarcity of Arabic test collections has long hindered information retrieval (IR) research over the Arabic Web. In this work, we present ArTest, the first large-scale test collection designed for the evaluation of ad-hoc search over the Arabic Web. ArTest uses ArabicWeb16, a collection of around 150M Arabic Web pages as the document collection, and includes 50 topics, 10,529 relevance judgments, and (more importantly) a rationale behind each judgment. To our knowledge, this is also the first IR test collection that includes rationales of primary assessors (i.e., topic developers) for their relevance judgments, exhibiting a useful resource for understanding the relevance phenomena. Finally, ArTest is made publicly-available for the research community.

While test collections provide the cornerstone of system-based evaluation in information retrieval, human relevance judging has become prohibitively expensive as collections have grown ever larger. Consequently, intelligently deciding which documents to judge has become increasingly important. We propose a two-phase approach to intelligent judging across topics which does not require document rankings from a shared task. In the first phase, we dynamically select the next topic to judge via a multi-armed bandit method. In the second phase, we employ active learning to select which document to judge next for that topic. Experiments on three TREC collections (varying scarcity of relevant documents) achieve t 0.90 correlation for [email protected] ranking and find 90% of the relevant documents at 48% of the original budget. To support reproducibility and follow-on work, we have shared our code online1.

Because it is expensive to construct test collections for Cranfield-based evaluation of information retrieval systems, a variety of lower-cost methods have been proposed. The reliability of these methods is often validated by measuring rank correlation (e.g., Kendall's tau) between known system rankings on the full test collection vs. observed system rankings on the lower-cost one. However, existing rank correlation measures do not consider the statistical significance of score differences between systems in the observed rankings. To address this, we propose two statistical-significance-aware rank correlation measures, one of which is a head-weighted version of the other. We first show empirical differences between our proposed measures and existing ones. We then compare the measures while benchmarking four system evaluation methods: pooling, crowdsourcing, evaluation with incomplete judgments, and automatic system ranking. We show that use of our measures can lead to different experimental conclusions regarding reliability of alternative low-cost evaluation methods.

Even though Web search engines play an important role in finding documents relevant to user queries, there is little to no attention given to how they perform in terms of usefulness for fact-checking claims. In this paper, we introduce a new research problem that addresses the ability of fact-checking systems to distinguish Web search results that are useful in discovering the veracity of claims from the ones that are not.We also propose a re-ranking method to improve ranking of search results for fact-checking. To evaluate our proposed method, we conducted a preliminary study for which we have developed a test collection that includes 22 claims and 20 manually-annotated Web search results for each. Our experiments show that the proposed method outperforms the baseline represented by the original ranking of search results. The contributions this improvement brings to real-world applications is two-fold: it will help human fact-checkers find useful documents for their task faster, and it will help automated fact-checking systems by pointing out which documents are useful and which are not.

While peer-agreement and gold checks are well-established methods for ensuring quality in crowdsourced data collection, we explore a relatively new direction for quality control: estimating work quality directly from workers’ behavioral traces collected during annotation. We propose three behavior-based models to predict label correctness and worker accuracy, then further apply model predictions to label aggregation and optimization of label collection. As part of this work, we collect and share a new Mechanical Turk dataset of behavioral signals judging the relevance of search results. Results show that behavioral data can be effectively used to predict work quality, which could be especially useful with single labeling or in a cold start scenario in which individuals’ prior work history is unavailable. We further show improvement in label aggregation and reducing labeling cost while ensuring data quality.

While crowdsourcing offers a low-cost, scalable way to collect relevance judgments, lack of transparency with remote crowd work has limited understanding about the quality of collected judgments. In prior work, we showed a variety of benefits from asking crowd workers to provide \em rationales for each relevance judgment \citemcdonnell2016relevant. In this work, we scale up our rationale-based judging design to assess its reliability on the 2014 TREC Web Track, collecting roughly 25K crowd judgments for 5K document-topic pairs. We also study having crowd judges perform topic-focused judging, rather than across topics, finding this improves quality. Overall, we show that crowd judgments can be used to reliably rank IR systems for evaluation. We further explore the potential of rationales to shed new light on reasons for judging disagreement between experts and crowd workers. Our qualitative and quantitative analysis distinguishes subjective vs.\ objective forms of disagreement, as well as the relative importance of each disagreement cause, and we present a new taxonomy for organizing the different types of disagreement we observe. We show that many crowd disagreements seem valid and plausible, with disagreement in many cases due to judging errors by the original TREC assessors. We also share our WebCrowd25k dataset, including: (1) crowd judgments with rationales, and (2) taxonomy category labels for each judging disagreement analyzed.

This paper presents LA3 , a scalable distributed system for graph analytics. LA3 couples a vertex-based programming model with a highly optimized linear algebra-based engine. It translates any vertex-centric program into an iteratively executed sparse matrix-vector multiplication (SpMV). To reduce communication and enhance scalability, the adjacency matrix representing an input graph is partitioned into locality-aware 2D tiles distributed across multiple processes. Alongside, three major optimizations are incorporated to preclude redundant computations and minimize communication. First, the link-based structure of the input graph is exploited to classify vertices into different types. Afterwards, vertices of special types are factored out of the main loop of the graph application to avoid superfluous computations. We refer to this novel optimization as computation filtering. Second, a communication filtering mechanism is involved to optimize for the high sparsity of the input matrix due to power-law distributions, common in real-world graphs. This optimization ensures that each process receives only the messages that pertain to non-zero entries in its tiles, substantially reducing communication traffic since most tiles are highly sparse. Lastly, a pseudo-asynchronous computation and communication optimization is proposed, whereby processes progress and communicate asynchronously, consume messages as soon as they become available, and block otherwise. We implemented and extensively tested LA3 on private and public clouds. Results show that LA3 outperforms six related state-of-the-art and popular distributed graph analytics systems by an average of 10X.

When collecting subjective human ratings of items, it can be difficult to measure and enforce data quality due to task subjectivity and lack of insight into how judges’ arrive at each rating decision. To address this, we propose requiring judges to provide a specific type of rationale underlying each rating decision. We evaluate this approach in the domain of Information Retrieval, where human judges rate the relevance of Webpages to search queries. Cost-benefit analysis over 10,000 judgments collected on Mechanical Turk suggests a win-win: experienced crowd workers provide rationales with almost no increase in task completion time while providing a multitude of further benefits, including more reliable judgments and greater transparency for evaluating both human raters and their judgments. Further benefits include reduced need for expert gold, the opportunity for dual-supervision from ratings and rationales, and added value from the rationales themselves.

Web crawls provide valuable snapshots of the Web which enable a wide variety of research, be it distributional analysis to characterize Web properties or use of language, content analysis in social science, or Information Retrieval (IR) research to develop and evaluate effective search algorithms. While many English-centric Web crawls exist, existing public Arabic Web crawls are quite limited, limiting research and development. To remedy this, we present ArabicWeb16, a new public Web crawl of roughly 150M Arabic Web pages with significant coverage of dialectal Arabic as well as Modern Standard Arabic. For IR researchers, we expect ArabicWeb16 to support various research areas: ad-hoc search, question answering, filtering, cross-dialect search, dialect detection, entity search, blog search, and spam detection. Combined use with a separate Arabic Twitter dataset we are also collecting may provide further value.