Query Logs Research Articles

ENRICH: A Query Rewriting Service Powered by Wikipedia Graph Structure

The search for relevant information in websites can be very frustrating for users who, unintentionally, use too general or inappropriate keywords to express their requests. To overcome this situation, query rewriting techniques aim at transforming the users requests to better describe the real intent of the users. However, to the best of our knowledge, current search tools either are too generic or require resources not available for everyone such as query log processors, natural language engines, etc. To supply this need, we present ENRICH, which is a query rewriting cloud service that is automatically tailored to each website and it is powered by an available, accessible and open resource: Wikipedia.

Identifying Microblogs for Targeted Contextual Advertising

Micro-blogging sites such as Facebook, Twitter, Google+ present a nice opportunity for targeting advertisements that are contextually related to the microblog content. By virtue of the sparse and noisy text makes identifying the microblogs suitable for advertising a very hard problem. In this work, we approach the problem of identifying the microblogs that could be targeted for advertisements as a two-step classification approach. In the first pass, microblogs suitable for advertising are identified. Next, in the second pass, we build a model to find the sentiment of the advertisable microblog. The systems use features derived from the Part-of-speech tags, the tweet content and uses external resources such as query logs and n-gram dictionaries from previously labeled data.This work aims at providing a thorough insight into the problem and analyzing various features to assess which features contribute the most towards identifying the tweets that can be targeted for advertisements.

Towards Supporting Search over Trending Events with Social Media

Many search engines identify bursts of activity around particular topics and reflect these back to users as Popular Now or Hot Searches. Activity around these topics typically evolves quickly in real-time during the course of a trending event. Users’ informational needs when searching for such topics will vary depending on the stage at which they engage with an event. Through a survey and log study, we observe that interaction with content about trending events varies significantly with prior awareness of the event. Building on this observation, we conduct a larger-scale analysis of query logs and social media data associated with hundreds of trending events. We find that search and social media activity tend to follow similar temporal patterns, but that social media activity leads by a few hours. While user interest in trending event content predictably diverges during peak activity periods, the overlap between content searched and shared increases. We discuss how these findings relate to the design of interfaces to better support sensemaking around trending events by integrating real-time social media content with traditional search results.

Is the Reign of Interactive Search Eternal? Findings from the Video Browser Showdown 2020

Comprehensive and fair performance evaluation of information retrieval systems represents an essential task for the current information age. Whereas Cranfield-based evaluations with benchmark datasets support development of retrieval models, significant evaluation efforts are required also for user-oriented systems that try to boost performance with an interactive search approach. This article presents findings from the 9th Video Browser Showdown, a competition that focuses on a legitimate comparison of interactive search systems designed for challenging known-item search tasks over a large video collection. During previous installments of the competition, the interactive nature of participating systems was a key feature to satisfy known-item search needs, and this article continues to support this hypothesis. Despite the fact that top-performing systems integrate the most recent deep learning models into their retrieval process, interactive searching remains a necessary component of successful strategies for known-item search tasks. Alongside the description of competition settings, evaluated tasks, participating teams, and overall results, this article presents a detailed analysis of query logs collected by the top three performing systems, SOMHunter, VIRET, and vitrivr. The analysis provides a quantitative insight to the observed performance of the systems and constitutes a new baseline methodology for future events. The results reveal that the top two systems mostly relied on temporal queries before a correct frame was identified. An interaction log analysis complements the result log findings and points to the importance of result set and video browsing approaches. Finally, various outlooks are discussed in order to improve the Video Browser Showdown challenge in the future.

The use of OPAC query logs to support evidence-informed information literacy (IL) training at The University of Dar es Salaam

This paper reports the results of the study which analysed OPAC users’ searching behaviour through the use of search queries. The study analysed how OPAC search queries can be used to assess the effectiveness of the information literacy programme offered by the University of Dar es Salaam. Data were collected unobtrusively and stored in the OPAC web server’s log file. OPAC search logs were qualitatively and quantitatively analysed to determine search patterns and search query formulation. Information literacy course contents were also qualitatively analysed and compared with users’ search activities. The results suggest that search query logs are essential and high quality evidence that can be used to inform information literacy pedagogical methods and course contents improvement. A comparison between OPAC users’ search behaviours and information lteracy course content identified some areas for readjusting the way information literacy instructions are delivered and improving OPAC search functionalities. The study has contributed to the conceptual understanding and the use of evidence to support evidence-informed practices (EIPs) in delivering information literacy courses.

Spoken Conversational Context Improves Query Auto-completion in Web Search

Web searches often originate from conversations in which people engage before they perform a search. Therefore, conversations can be a valuable source of context with which to support the search process. We investigate whether spoken input from conversations can be used as a context to improve query auto-completion. We model the temporal dynamics of the spoken conversational context preceding queries and use these models to re-rank the query auto-completion suggestions. Data were collected from a controlled experiment and comprised conversations among 12 participant pairs conversing about movies or traveling. Search query logs during the conversations were recorded and temporally associated with the conversations. We compared the effects of spoken conversational input in four conditions: a control condition without contextualization; an experimental condition with the model using search query logs; an experimental condition with the model using spoken conversational input; and an experimental condition with the model using both search query logs and spoken conversational input. We show the advantage of combining the spoken conversational context with the Web-search context for improved retrieval performance. Our results suggest that spoken conversations provide a rich context for supporting information searches beyond current user-modeling approaches.

The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval.

This paper describes in detail VISIONE, a video search system that allows users to search for videos using textual keywords, the occurrence of objects and their spatial relationships, the occurrence of colors and their spatial relationships, and image similarity. These modalities can be combined together to express complex queries and meet users’ needs. The peculiarity of our approach is that we encode all information extracted from the keyframes, such as visual deep features, tags, color and object locations, using a convenient textual encoding that is indexed in a single text retrieval engine. This offers great flexibility when results corresponding to various parts of the query (visual, text and locations) need to be merged. In addition, we report an extensive analysis of the retrieval performance of the system, using the query logs generated during the Video Browser Showdown (VBS) 2019 competition. This allowed us to fine-tune the system by choosing the optimal parameters and strategies from those we tested.

A Pattern Driven Graph Ranking Approach to Attribute Extraction for Knowledge Graph

Attribution extraction refers to find the attributes for the instances of a given semantic class, which is essential to enhance the schema of a knowledge graph. To facilitate the attribution extraction from the query log, this article proposes a pattern driven graph ranking approach to jointly employ the pattern and context distribution information. First, a simple pattern on query text is applied to automatically acquire seed attributes. Then, a graph-based weight propagation is designed to rank the patterns by context distribution algorithm information. Experimental results show that, on a Chinese query log collected by Baidu, the automatically acquired seeds are more representative than the classical manually assembled seeds, achieving an improvement of 11.6% in MAP as compared to the baseline approach. And the graph-based ranking algorithm manipulates the two types of evidence more effectively, outperforming both the distributional similarity based baseline and the HITS algorithm by 29.2% and 11.3%, respectively.

Evaluation of Machine Learning Algorithms in Predicting the Next SQL Query from the Future

Prediction of the next SQL query from the user, given her sequence of queries until the current timestep, during an ongoing interaction session of the user with the database, can help in speculative query processing and increased interactivity. While existing machine learning-- (ML) based approaches use recommender systems to suggest relevant queries to a user, there has been no exhaustive study on applying temporal predictors to predict the next user issued query. In this work, we experimentally compare ML algorithms in predicting the immediate next future query in an interaction workload, given the current user query or the sequence of queries in a user session thus far. As a part of this, we propose the adaptation of two powerful temporal predictors: (a) Recurrent Neural Networks (RNNs) and (b) a Reinforcement Learning approach called Q-Learning that uses Markov Decision Processes. We represent each query as a comprehensive set of fragment embeddings that not only captures the SQL operators, attributes, and relations but also the arithmetic comparison operators and constants that occur in the query. Our experiments on two real-world datasets show the effectiveness of temporal predictors against the baseline recommender systems in predicting the structural fragments in a query w.r.t. both quality and time. Besides showing that RNNs can be used to synthesize novel queries, we find that exact Q-Learning outperforms RNNs despite predicting the next query entirely from the historical query logs.

Exploiting temporal changes in query submission behavior for improving the search engine result cache performance

A commonly used technique for improving query response time in retrieval systems is storing query-relevant information in a fast access memory storage such as a result cache. The effectiveness of the result cache heavily relies on giving correct admission and eviction decisions, which require careful analysis of query and stream characteristics. Due to anonymous and global user access patterns, search engines are often considered time-invariant architectures: query characteristics are frequently collected globally, and assumed to be unchanging for long periods of time. However, the highly distributed nature of the modern search engine framework consequently led to noticeable temporal changes in user access patterns through short periods of time for each of the data center within the distributed network.The work presented here attempts to evaluate temporal variations in query submissions and exploit them in order to improve the result caching performance. To this end, query logs are analyzed in order to verify the availability of such variations and a new caching framework that facilitate these changes is proposed. The proposed framework partitions the result cache into three segments: a static segment that stores the most frequent queries in an offline fashion, a newly introduced semi-static segment on top of the state-of-the-art Static–Dynamic Cache (SDC) that changes content during different periods of the day, and a dynamic segment that is maintained in an Least Recently Used (LRU) fashion. Conducted experiments demonstrate that the proposed caching framework improves the hit rate of a search engine result cache up to 3.31% and query response time up to 7.27% with respect to the state-of-the-art techniques.

A new Query Reformulation Approach using Web Result Clustering and User Profile

Query reformulation techniques are essential for information retrieval systems. These techniques eliminate the bad queries (short and ambiguous queries) and minimize users search time. There are two kinds of techniques in literature; the first uses the query logs with the click-through data to identify relevant queries and propose them to the user. The second group uses relevant terms extracted from different sources such as Wikipedia, Wordnet, and pseudo-relevant documents to expand the initial query and increase the likelihood with relevant documents. Both groups generate false queries because they do not consider the user interests and due to the assumption that the user clicks only on relevant results (first group) and that the top-k retrieved documents (top 5 to 15) are relevant (second group).In this paper, we propose a novel approach to reformulate the user queries using his profile (which contains the user interests). The approach retrieves documents related to the query from four different data sources (≈ 1000 doc). Then, it extracts the topics of these documents using the Lingo clustering algorithm (cluster the document with the same topic) and Text razor API (extract the potential topics of each cluster). Finally, it generates queries based on these topics and the user profile. The results show that the proposed approach outperforms the existing solution in P@10, P@20, and MAP.

Multi-Group ObScure Logging (MG-OSLo) A Privacy-Preserving Protocol for Private Web Search

The Web Search Engine (WSE) is a software system used to retrieve data from the web successfully. WSE uses the user’s search queries to build the user’s profile and provide personalized results. Users’ search queries hold identifiable information that could compromise the privacy of the respective user. This work proposes a multi-group distributed privacy-preserving protocol (MG-OSLo) and tries to investigate the state-of-the-art distributed privacy-preserving protocols for computing web search privacy. The MG-OSLo comprises multiple groups in which each group has a fixed number of users. The MG-OSLo measures the impact of the multi-group on the user’s privacy. The primary objective of this work is to assess local privacy and profile privacy. It aims at evaluating the impact of group size and group count on a user’s privacy. Two grouping approaches are used to group the users in MG-OSLo, i.e. a non-overlapping group design and overlapping group design. The local privacy results reveal that the probability of linking a query to the user depends on the group size and group count. The higher the group size or group count, the lower the likelihood of relating the query to the user. The profile privacy computes the profile obfuscation level using a privacy metric Profile Exposure Level (PEL). Different experiments have been performed to compute the profile privacy of the subset of an AOL query log for two situations: i) self-query submissions allowed and ii) self-query submissions not allowed. The privacy achieved by MG-OSLo is compared with the modern privacy-preserving protocol UUP(e), OSLo, and Co-utile protocols. The results show that the MG-OSLo provided better results as compared to OSLo, UUP, and Co-utile. Similarly, the multi-group has a positive impact on local privacy and user profile privacy.

Burstiness-Aware Web Search Analysis on Different Levels of Evidences

Personalizing the analysis for web search potentially improves the search experience. A good analytical model for web search should leverage not only collective wisdom but also individual characteristics. Most of the existing analytical models, however, focus on how to utilize the collective wisdom, from a crowd, for instance. In this paper, we address the problem of user-specific web search analysis by considering the so-called burstiness in web search, which captures the behavior of rare words appearing many times in a single document. We go beyond click graph and propose two probabilistic topic models, Topic Independence Model and Topic Dependence Model. The former adopts the assumption that the generation of query terms and URLs are topically independent, and the latter captures the coupling between search queries and URLs. We also capture the temporal burstiness of topics by utilizing continuous Beta distribution. Through a large-scale analysis of a real-life search query log, we observe that each user's web search trail enjoys multiple kinds of user-based unique characteristics. On a massive search query log, the new models achieve a better held-out likelihood than existing baselines, and they can also effectively reveal the latent evolution of topics on the corpus level and user-based level.

Hybrid Query Execution on Linked Data With Complete Results

The link traversal strategies to query Linked Data over WWW can retrieve up-to-date results using a recursive URI lookup process in real-time. The downside of this approach comes with the query patterns having subject unbound (i.e. ?S rdf:type:Class). Such queries fail to start up the traversal process as the RDF pages are subject-centric in nature. Thus, zero-knowledge link traversal leads to the empty query results for these queries. In this paper, the authors analyze a large corpus of real-world SPARQL query logs and identify the Most Frequent Predicates (MFPs) occurring in these queries. The knowledge of these MFPs helps in finding and indexing a limited number of triples from the original data set. Additionally, the authors propose a Hybrid Query Execution (HQE) approach to execute the queries over this index for initial data source selection followed by link traversal process to fetch complete results. The evaluation of HQE on the latest real data benchmarks reveals that it retrieves at least five times more results than the existing approaches.

Random Forest Bagging and X‐Means Clustered Antipattern Detection from SQL Query Log for Accessing Secure Mobile Data

In the current ongoing crisis, people mostly rely on mobile phones for all the activities, but query analysis and mobile data security are major issues. Several research works have been made on efficient detection of antipatterns for minimizing the complexity of query analysis. However, more focus needs to be given to the accuracy aspect. In addition, for grouping similar antipatterns, a clustering process was performed to eradicate the design errors. To address the above‐said issues and further enhance the antipattern detection accuracy with minimum time and false positive rate, in this work, Random Forest Bagging X‐means SQL Query Clustering (RFBXSQLQC) technique is proposed. Different patterns or queries are initially gathered from the input SQL query log, and bootstrap samples are created. Then, for each pattern, various weak clusters are constructed via X‐means clustering and are utilized as the weak learner (clusters). During this process, the input patterns are categorized into different clusters. Using the Bayesian information criterion, the similarity measure is employed to evaluate the similarity between the patterns and cluster weight. Based on the similarity value, patterns are assigned to either relevant or irrelevant groups. The weak learner results are aggregated to form strong clusters, and, with the aid of voting, a majority vote is considered for designing strong clusters with minimum time. Experiments are conducted to evaluate the performance of the RFBXSQLQC technique using the IIT Bombay dataset using the metrics like antipattern detection accuracy, time complexity, false-positive rate, and computational overhead with respect to the differing number of queries. The results revealed that the RFBXSQLQC technique outperforms the existing algorithms by 19% with pattern detection accuracy, 34% minimized time complexity, 64% false-positive rate, and 31% in terms of computational overhead.

Surveillance of early stage COVID-19 clusters using search query logs and mobile device-based location information

Two clusters of the coronavirus disease 2019 (COVID-19) were confirmed in Hokkaido, Japan, in February 2020. To identify these clusters, this study employed web search query logs of multiple devices and user location information from location-aware mobile devices. We anonymously identified users who used a web search engine (i.e., Yahoo! JAPAN) to search for COVID-19 or its symptoms. We regarded them as web searchers who were suspicious of their own COVID-19 infection (WSSCI). We extracted the location of WSSCI via a mobile operating system application and compared the spatio-temporal distribution of WSSCI with the actual location of the two known clusters. In the early stage of cluster development, we confirmed several WSSCI. Our approach was accurate in this stage and became biased after a public announcement of the cluster development. When other cluster-related resources, such as detailed population statistics, are not available, the proposed metric can capture hints of emerging clusters.

2019 Tony Kent Strix Memorial Award Winner

In 2019, the UK electronic information Group (UKeiG), in partnership with the International Society for Knowledge Organisation UK (ISKO UK), the Royal Society of Chemistry Chemical Information and Computer Applications Group (RSC CICAG) and the British Computer Society Information Retrieval Specialist Group (BCS IRSG), was delighted to announce that the winner of the prestigious Tony Kent Strix Memorial Award for 2019, in recognition of his major and sustained contributions to the field of information retrieval, was Professor Ingemar J. Cox, Department of Computer Science at University College London.
 Professor Cox is Head of UCL’s Media Futures Research Group and a Professor at the Department of Computer Science at the University of Copenhagen. His current research interests include information retrieval and data analytics of online social media, twitter and query logs.

When Are Search Completion Suggestions Problematic?

Problematic web search query completion suggestions-perceived as biased, offensive, or in some other way harmful-can reinforce existing stereotypes and misbeliefs, and even nudge users towards undesirable patterns of behavior. Locating such suggestions is difficult, not only due to the long-tailed nature of web search, but also due to differences in how people assess potential harms. Grounding our study in web search query logs, we explore when system-provided suggestions might be perceived as problematic through a series of crowd-experiments where we systematically manipulate: the search query fragments provided by users, possible user search intents, and the list of query completion suggestions. To examine why query suggestions might be perceived as problematic, we contrast them to an inventory of known types of problematic suggestions. We report our observations around differences in the prevalence of a) suggestions that are problematic on their own versus b) suggestions that are problematic for the query fragment provided by a user, for both common informational needs and in the presence of web search voids-topics searched by few to no users. Our experiments surface a rich array of scenarios where suggestions are considered problematic, including due to the context in which they were surfaced. Compounded by the elusive nature of many such scenarios, the prevalence of suggestions perceived as problematic only for certain user inputs, raises concerns about blind spots due to data annotation practices that may lead to some types of problematic suggestions being overlooked.

Investigating COVID-19-Related query logs of Chinese search engine users.

Query logs include valuable information for understanding user intent and behavior in Web search. In this article, we investigate COVID‐19‐related query logs by dividing search sessions into different intent and analyzing the user behavior of groups and individuals. We believe it important to learn about the epidemic's influence on users' search behavior and refine search engine to confront similar epidemic outbreaks in the future.

On the Usefulness of SQL-Query-Similarity Measures to Find User Interests

In the sciences and elsewhere, the use of relational databases has become ubiquitous. An important challenge is finding hot spots of user interests. In principle, one can discover user interests by clustering the queries in the query log. Such a clustering requires a notion of query similarity. This, in turn, raises the question of what features of SQL queries are meaningful. We have studied the query representations proposed in the literature and corresponding similarity functions and have identified shortcomings of all of them. To overcome these limitations, we propose new similarity functions for SQL queries. They rely on the so-called access area of a query and, more specifically, on the overlap and the closeness of the access areas. We have carried out experiments systematically to compare the various similarity functions described in this article. The first series of experiments measures the quality of clustering and compares it to a ground truth. In the second series, we focus on the query log from the well-known SkyServer database. Here, a domain expert has interpreted various clusters by hand. We conclude that clusters obtained with our new measures of similarity seem to be good indicators of user interests.