In politically charged environments, understanding how ideological narratives emerge, spread, and shape user behavior on social media is critical for applications ranging from misinformation detection to enriching public discourse with verifiable truth. In this study, we present NARRA-SCALE, a framework that brings together network analysis, narrative detection, stance classification, and bipartite scaling to place users, communities, and messages along a single ideological dimension. As a case study, we apply NARRA-SCALE to a U.S. race relations related dataset chiefly polarized between “Black Lives Matter” and “All Lives Matter” supporters. We extract topic coded key phrases and named entities using frequency-based heuristics. Using key phrase co-occurrence relationships and latent representations of matching messages, we mine grouped (entities, issues/aspects, values) triplets characterizing key recurring narratives within the corpus. We use an LLM to summarize messages matching each triplet. Subsequently, a panel of experts label the stance information of the narratives on their key phrases, enabling weak supervision for training a high-accuracy stance detection model which achieves an 81 % F1 score on a held-out gold standard. Next, we construct a signed bipartite graph with colored edges (i.e., representing support versus opposition) between users and key terms mentioned in their messaging corresponding to debated core values, issues, and actors to co-scale their positions on a [-1,+1] range. Our method reaches 91 % agreement with user groups identified through community structure as well as with the “ideal points” of political elites and the general public on Twitter in the U.S. and five European countries.

ABSTRACT Computing betweenness centrality (BC) in large graphs is crucial for various applications, including telecommunications, social, and biological networks. However, the huge size of the data presents significant challenges. In this paper, we introduce a novel approximate approach for efficiently extracting top k BC nodes by combining the Louvain community detection algorithm with Brandes' algorithm. Our method significantly enhances the runtime efficiency of the traditional Brandes' algorithm while preserving accuracy across both synthetic and real‐world datasets. Additionally, our approach is suitable for parallelization, further improving its efficiency. Experimental results confirm the effectiveness of our method for large and sparse graphs.

In the big data era, automated index selection and recommendation has been an important research problem to improve the data access efficiency. Previous efforts on artificial intelligence based database index selection have focused on relational databases. In this work, we consider the automated index selection for NoSQL databases and investigate the feasibility of supervised learning and reinforcement learning based solutions. The experiments conducted on the YCSB dataset show that reinforcement learning improves index selection performance as in relational databases, and supervised learning gives promising results and can be considered applicable under sufficient amount of training data.

Abstract The Floyd‐Warshall algorithm is the most popular algorithm for determining the shortest paths between all vertex pairs in a graph. It is a very simple and an elegant algorithm. However, for graphs without any negative weighted edges, using Dijkstra's shortest path algorithm for every vertex as a source vertex to produce all‐pairs shortest paths works significantly better than the Floyd‐Warshall algorithm, especially for large graphs. Furthermore, for graphs with negative weighted edges, with no negative cycle, in general Johnson's algorithm also performs better than the Floyd‐Warshall algorithm for large graphs. Johnson's algorithm first transforms the graph into a non‐negative one by using the Bellman‐Ford algorithm, then applies the Dijkstra's algorithm to the transformed graph. Thus, mainly, the Floyd‐Warshall algorithm is quite inefficient, especially for large graphs. In this paper, we show a simple improvement on the Floyd‐Warshall algorithm that will increases its efficiency, especially for very sparse graphs (i.e., the number of its edges is less than the number of its vertices), so it can be used instead of more complicated alternatives. We also show that our approach is also very effective for denser disconnected graphs. Since the new algorithm modifies the original Floyd‐Warshall algorithm, it is mainly aimed for directed graphs without negative cycles. Most programmers prefer to implement the Floyd‐Warshall algorithm over more complicated but more efficient alternatives for solving all‐pairs shortest path problems. In this work, we show that without the addition of any complicated data structures, the performance of the Floyd‐Warshall algorithm can be improved very easily. Our practical approach works even better than its alternatives for large sparse graphs.

Social media has become an important place for online marketing like never before. Businesses use various techniques to identify and reach potential customers across multiple platforms and deliver a message to grab their attention. A notable post could attract potential customers to the product landing page. However, the acquisition is only the beginning. The landing page should respond to the visitor's need for persuasion to increase conversion rates. Showing every visitor the same page is far from that goal. Even if the product meets everyone's needs, their priorities may differ. In this study, we propose a pipeline that includes gathering and identifying potential customers from Twitter, determining their priorities by understanding the context of their message, and creating a coherent paragraph that addresses the issue to display on the landing page.

In this paper, we present a framework for predicting the personality traits by analyzing tweets written in Turkish. The prediction model is constructed with a clustering based approach. Since the model is based on linguistic features, it is language specific. The prediction model uses features applicable to Turkish language and related to writing style of Turkish Twitter users. Our approach uses anonymous BIG5 questionnaire scores of volunteer participants as the ground truth in order to generate personality model from Twitter posts. Experiment results show that constructed model can predict personality traits of Turkish Twitter users with relatively small errors.

Automated Telling Machines (ATM) are one of the prominent services of the banks, which facilitate daily banking operations. Among the offered services, money withdrawal is a very basic functionality of ATMs. For the banks, it is important to manage the amount of money to be loaded in ATMs. Hence, prediction of the withdrawal amount is an important step in the ATM management. In this work, we investigate the performance of deep learning techniques for ATM money withdrawal amount prediction problem. The problem is defined in two ways: predicting the amount of money to be withdrawn, and predicting the class label of the withdrawal amount. Our data set includes daily total withdrawal amounts together with the date information. In our experiments, we further analyzed the effect of additional information, such as size of history window, weather condition, currency rate and location. For numeric value prediction task, we compared the prediction performance with statistical models of ARIMA and SARIMA. The experiments show that the neural architectures are feasible for the task of withdrawal amount prediction. They can especially provide high accuracy results when the problem is modeled as a class label prediction task.

Objective: We aim to deliver a framework with 2 main objectives: 1) facilitating the design of theory-driven, adaptive, digital interventions addressing chronic illnesses or health problems and 2) producing personalized intervention delivery strategies to support self-management by optimizing various intervention components tailored to people's individual needs, momentary contexts, and psychosocial variables. Materials and Methods: We propose a template-based digital intervention design mechanism enabling the configuration of evidence-based, just-in-time, adaptive intervention components. The design mechanism incorporates a rule definition language enabling experts to specify triggering conditions for interventions based on momentary and historical contextual/personal data. The framework continuously monitors and processes personal data space and evaluates intervention-triggering conditions. We benefit from reinforcement learning methods to develop personalized intervention delivery strategies with respect to timing, frequency, and type (content) of interventions. To validate the personalization algorithm, we lay out a simulation testbed with 2 personas, differing in their various simulated real-life conditions. Results: We evaluate the design mechanism by presenting example intervention definitions based on behavior change taxonomies and clinical guidelines. Furthermore, we provide intervention definitions for a real-world care program targeting diabetes patients. Finally, we validate the personalized delivery mechanism through a set of hypotheses, asserting certain ways of adaptation in the delivery strategy, according to the differences in simulation related to personal preferences, traits, and lifestyle patterns. Conclusion: While the design mechanism is sufficiently expandable to meet the theoretical and clinical intervention design requirements, the personalization algorithm is capable of adapting intervention delivery strategies for simulated real-life conditions.

Event detection is a popular research problem, aiming to detect events from online data sources with least possible delay. Most of the previous work focus on analyzing textual content such as social media postings to detect happenings. In this work, we consider event detection as a change detection problem in network structure, and propose a method that detects change in community structure extracted from communication network. We study three versions of the method based on different change models. Experimental analysis on benchmark data set reveals that change in the community can be used as an indication of an event.

The web provides a suitable media for users to post comments on different topics. In most of such content, authors express different opinions on different features or aspects of the topic. In aspect based sentiment analysis, it is analyzed as to for which aspect which opinion is expressed. Once aspects are available, the next important step is to match aspects with correct sentiments. In this work, we investigate enhancements for two cases in matching step: extracting implicit aspects, and sentiment words whose polarity depends on the aspect. The techniques are applied on Turkish informal texts collected from a products forum. Experimental evaluation shows that additional steps applied for these cases improve the accuracy of aspect based sentiment analysis.

In this paper, we propose a new algorithm, called STRICLUSTER, to find tri-clusters from signed 3-partite graphs. The dataset contains three different types of nodes. Hyperedges connecting three nodes from three different partitions represent either positive or negative relations among those nodes. The aim of our algorithm is to find clusters with strong positive relations among its nodes. Moreover, negative relations up to a certain threshold is also allowed. Also, the clusters can have no overlapping hyperedges. We show the effectiveness of our algorithm via several experiments.

In recent years, using cell phone log data to model human mobility patterns became an active research area. This problem is a challenging data mining problem due to huge size and non-uniformity of the log data, which introduces several granularity levels for the specification of temporal and spatial dimensions. This paper focuses on the prediction of the location of the next activity of the mobile phone users. There are several versions of this problem. In this work, we have concentrated on the following three problems: predicting the location and the time of the next user activity, predicting the location of the next activity of the user when the location of the user changes, and predicting both the location and the time of the activity of the user when the user's location changes. We have developed sequential pattern mining-based techniques for these three problems and validated the success of these methods with real data obtained from one of the largest mobile phone operators in Turkey. Our results are very encouraging, since we were able to obtain quite high accuracy results under small prediction sets.

In this work, a new fast dynamic community detection algorithm for large scale networks is presented. Most of the previous community detection algorithms are designed for static networks. However, large scale social networks are dynamic and evolve frequently over time. To quickly detect communities in dynamic large scale networks, we proposed dynamic modularity optimizer framework (DMO) that is constructed by modifying well-known static modularity based community detection algorithm. The proposed framework is tested using several different datasets. According to our results, community detection algorithms in the proposed framework perform better than static algorithms when large scale dynamic networks are considered.

Our goal in this paper is to design cost-aware result caching approaches for meta-search engines. We introduce different levels of eviction, namely, query-, resource- and entry-level, based on the granularity of the entries to be evicted from the cache when it is full. We also propose a novel entry-level caching approach that is tailored for the meta-search scenario and superior to alternative approaches.

In this paper, we propose a new model to integrate additional data, which is obtained from geospatial resources other than original data set in order to improve Location/Activity recommendations. The data set that is used in this work is a GPS trajectory of some users, which is gathered over 2 years. In order to have more accurate predictions and recommendations, we present a model that injects additional information to the main data set and we aim to apply a mathematical method on the merged data. On the merged data set, singular value decomposition technique is applied to extract latent relations. Several tests have been conducted, and the results of our proposed method are compared with a similar work for the same data set.

In this paper, sentiment classification techniques are incorporated into the domain of political news from columns in different Turkish news sites. We compared four supervised machine learning algorithms of Naïve Bayes, Maximum Entropy, SVM and the character based N-Gram Language Model for sentiment classification of Turkish political columns. We also discussed in detail the problem of sentiment classification in the political news domain. We observe from empirical findings that the Maximum Entropy and N-Gram Language Model outperformed the SVM and Naïve Bayes. Using different features, all the approaches reached accuracies of 65% to 77%.

Within the scope of information retrieval, efficient similarity search in large document or multimedia collections is a critical task. In this paper, we present a rigorous comparison of three different approaches to the image retrieval problem, including cluster-based indexing, distance-based indexing, and multidimensional scaling methods. The time and accuracy trade-offs for each of these methods are demonstrated on a large Corel image database. Similarity of images is obtained via a feature-based similarity measure using four MPEG-7 low-level descriptors. We show that an optimization of feature contributions to the distance measure can identify irrelevant features and is necessary to obtain the maximum accuracy. We further show that using multidimensional scaling can achieve comparable accuracy, while speeding-up the query times significantly by allowing the use of spatial access methods.

In this paper, we propose a novel framework called Smart-Miner for web usage mining problem which uses link information for producing accurate user sessions and frequent navigation patterns. Unlike the simple session concepts in the time and navigation based approaches, where sessions are sequences of web pages requested from the server or viewed in the browser, Smart Miner sessions are set of paths traversed in the web graph that corresponds to users' navigations among web pages. We have modeled session construction as a new graph problem and utilized a new algorithm, Smart-SRA, to solve this problem efficiently. For the pattern discovery phase, we have developed an efficient version of the Apriori-All technique which uses the structure of web graph to increase the performance. From the experiments that we have performed on both real and simulated data, we have observed that Smart-Miner produces at least 30% more accurate web usage patterns than other approaches including previous session construction methods. We have also studied the effect of having the referrer information in the web server logs to show that different versions of Smart-SRA produce similar results. Our another contribution is that we have implemented distributed version of the Smart Miner framework by employing Map/Reduce Paradigm. We conclude that we can efficiently process terabytes of web server logs belonging to multiple web sites by our scalable framework.

New protein structures are continuously being determined with the hope of deriving insights into the function and mechanisms of proteins, and consequently, protein structure repositories are growing by leaps and bounds. However, we are still far from having the right methods for sensitive and effective use of the available structural data. The fact that current structural analysis tools are impractical for large-scale applications have given rise to several approaches that try to quickly identify candidate proteins worthy of further analysis. Nonetheless, these approaches do not provide the desired sensitivity of identifying important structural similarities. In this study, we propose a new protein structure retrieval method (RCIndex: Residue-Contacts Index) that is based on accurate and efficient identification of similar residue contacts from a database of available protein structures. By defining a metric distance function for biologically meaningful comparison of residue contacts, distance-based indexing is made applicable for quick retrieval of similar residue contact seeds. These seeds are extended into high scoring segment pairs, which induce structural superpositions. The results show that RCIndex is effective in not only identifying related proteins, but also producing remarkably high quality structural alignments that are comparable to or better than those produced by popular pairwise alignment tools. To the best of our knowledge, this is the first time the protein structure retrieval and alignment tasks are successfully handled together.

MOTIVATION: Identification and comparison of similar three-dimensional (3D) protein structures has become an even greater challenge in the face of the rapidly growing structure databases. Here, we introduce Vorometric, a new method that provides efficient search and alignment of a query protein against a database of protein structures. Voronoi contacts of the protein residues are enriched with the secondary structure information and a metric substitution matrix is developed to allow efficient indexing. The contact hits obtained from a distance-based indexing method are extended to obtain high-scoring segment pairs, which are then used to generate structural alignments. RESULTS: Vorometric is the first to address both search and alignment problems in the protein structure databases. The experimental results show that Vorometric is simultaneously effective in retrieving similar protein structures, producing high-quality structure alignments, and identifying cross-fold similarities. Vorometric outperforms current structure retrieval methods in search accuracy, while requiring com-parable running times. Furthermore, the structural superpositions produced are shown to have better quality and coverage, when compared with those of the popular structure alignment tools. AVAILABILITY: Vorometric is available as a web service at http://bio.cse.ohio-state.edu/Vorometric

Sequence similarity search of proteins is one of the basic and most common steps followed in bioninformatics research and is used in making evolutionary, structural, and functional inferences. The quality of the search and the alignment of the protein sequences depend crucially on the underlying amino-acid substitution matrix. We present a method for deriving amino acid substitution matrices from 4-body contact propensities of amino-acids in 3D protein structures. Unlike current popular methods, our method does not rely on mutational analysis, evolutionary arguments, or alignment of protein sequences or structures. The alignment accuracy of our derived matrices is evaluated using the BAliBASE reference alignment set and is found to be comparable to that of popular matrices from the literature. Notably, the metric subset of our matrices outperform other available metric matrices. Our matrices will be useful especially in the development of empirical potential energy functions and in distance-based sequence indexing. Supplementary Material: Our substitution matrices and detailed alignment data can be obtained from http://www.ceng.metu.edu.tr/~ahmet/bioinfo/distmat

Producing answers to a set of queries with common tasks efficiently is known as the multiple-query optimization (MQO) problem. Each query can have several alternative evaluation plans, each with a different set of tasks. Therefore, the goal of MQO is to choose the right set of plans for queries which minimizes the total execution time by performing common tasks only once. Since MQO is an NP-hard problem, several, mostly heuristics based, solutions have been proposed for solving it. To the best of our knowledge, this correspondence is the first attempt to solve MQO using an evolutionary technique, genetic algorithms

One of the popular trends in computer science has been development of intelligent web-based systems. Demand for such systems forces designers to make use of knowledge discovery techniques on web server logs. Web usage mining has become a major area of knowledge discovery on World Wide Web. Frequent pattern discovery is one of the main issues in web usage mining. These frequent patterns constitute the basic information source for intelligent web-based systems. In this paper; frequent pattern mining algorithms for web log data and their performance comparisons are examined. Our study is mainly focused on finding suitable pattern mining algorithms for web server logs.

View maintenance for intentional relations is one of the most active research topics in deductive databases. The simplest, but the most frequently found form of the recursive relations in deductive databases is transitive-closure relations. Materialized transitive closure view definitions and maintenance of these views under updates on the base relations, is one of the techniques for the view maintenance of transitive closure relations. In this paper a special data structure is presented that represents transitive closure relation in compressed form. Update operations on this structure are defined and their algorithms are given. Unlike previous proposals, the technique presented in this paper treats cyclic and acyclic relations in the same way without requiring the determination of cycles after the update operations. The materialized form of the transitive closure relation is also suitable for different forms of ransitive closure queries.Request access from your librarian to read this article's full text.

The development of efficient algorithms to process the different forms of transitive-closure (TC) queries within the context of large database systems has recently attracted a large volume of research efforts. In this paper, we present two new algorithms suitable for processing one of these forms, the so called strong partially instantiated transitive closure, in which one of the query's arguments is instantiated to a set of constants and the processing of which yields a set of tuples that draw their values from both of the query's instantiated and uninstantiated arguments. These algorithms avoids the redundant computations and high storage cost found in a number of similar algorithms. Using simulation, this paper compares the performance of the new algorithms with those found in literature and shows clearly the superiority of the new algorithms.

The development of efficient algorithms to process the different forms of transitive-closure queries within the context of large database systems has attracted a large volume of research efforts. The authors present a new algorithm that is suitable for processing one of these forms, the strong partially instantiated query, in which one of the query's arguments is instantiated to a set of constants. The processing of this algorithm yields a set of tuples that draw their values from both of the query's instantiated and uninstantiated arguments. This algorithm avoids the redundant computations and the high storage costs found in a number of similar algorithms.>

An algorithm suitable for the full transitive closure problem, which is used to solve uninstantiated recursive queries in deductive databases, is presented. In this algorithm there are two phases. In the first phase a general graph is condensed into an acyclic graph and at the same time a special sparse matrix is formed from the acyclic graph. The second phase is the main one, where all of the page I/O operations are minimized. Simulation is used to study the performance of this algorithm and compare it with that of previous algorithms.>