No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A novel approach for efficient stance detection in online social networks with metaheuristic optimization
Abstract
In the 19th and 20th centuries, social networks have been an important topic in a wide range of fields from sociology to education. However, with the advances in computer technology in the 21st century, significant changes have been observed in social networks, and conventional networks have evolved into online social networks. The size of these networks, along with the large amount of data they generate, has introduced new social networking problems and solutions. Social network analysis methods are used to understand social network data. Today, several methods are implemented to solve various social network analysis problems, albeit with limited success in certain problems. Thus, the researchers develop new methods or recommend solutions to improve the performance of the existing methods. In the present paper, a novel optimization method that aimed to classify social network analysis problems was proposed. The problem of stance detection, an online social network analysis problem, was first tackled as an optimization problem. Furthermore, a new hybrid metaheuristic optimization algorithm was proposed for the first time in the current study, and the algorithm was compared with various methods. The analysis of the findings obtained with accuracy, precision, recall, and F-measure classification metrics demonstrated that our method performed better than other methods.
... Three years later, in 2020, this number reached 3 billion people. This number is expected to reach 4.41 billion people in 2025 (Can and Alatas, 2021a). Considering the large number of nodes in these networks and the edges between them, it is clear that these networks offer great opportunities for new research. ...
... Also, genetics is common to Atlantic façade Euro-African populations and Northern Africa and Arabic Peninsula (Arnaiz-Villena et al., 2017;Hajjej et al., 2018). It is inferred that circum-Mediterranean contacts during thousand years constructed Mediterranean cultures from Canary Islands to Ancient Persia (Arnaiz-Villena et al., 1999;2021a) and this is the origin of Classical Mediterranean cultures that was later exclusively attributed toRome and Greece ( Figure 3). 2) Mediterranean culture is constructed by interactions of both Africans and Europeans living together during thousands of years between North European Ices and Sahara Desert. ...
... These types of constructions have been found around Mediterranean Sea and Northern Africa, including nowadays Sahara Desert (Arnaiz-Villena et al., 2019a;. Obviously, these buildings found in Desert were most probably constructed in a greener Epoch, when Sahara was humid before 6,000 years BC (Arnaiz-Villena et al, 1999;2021a). In addition, cart-ruts there exist: they are rock-carved channels and crests that cannot be made by cart wheels because of frequent non-parallel and unusual unexpected bends which are impossible to carts for circulating. ...
One of the crucial factors for improving agricultural productivity is using image processing
techniques and hyperspectral Remote Sensing applications. It is presented a short inquiry on usage of image processing techniques and hyperspectral sensors for helping researchers and farmers to precise agricultural practices including weed and herbicide technologies, monitoring plant growth and plant nutrition management. Hyperspectral sensors are devices that acomplishes images over hundreds of spectral bands, thereby enabling the extraction of spectral signatures for objects or materials observed. Hyperspectral remote sensing has been used over a sheer variety of applications, such as agriculture, forestry, geology, ecological monitoring and disaster monitoring. Observations is used to optimize the utilization of resources and management of farming practices such as usage of hyperspectral image processing in the monitoring of plant diseases, insect pests and invasive plant species; the estimation of crop yield; and the fine classification of crop distributions. This paper presents an in-depth overview of hyperspectral data processing techniques and suggestions for making progress in the agricultural applications of hyperspectral technologies.
... In the Big Crunch phase, the randomly distributed solutions are rearranged, and a novel solution is determined by evaluating the center of mass. 7,38 The formula for evaluating the center of mass (x c ) is described in Eq. (1). ...
... The normal distribution operation is performed in every direction around the center of mass, where the standard deviation of distribution decreases with the increase in iteration number. 38 This convergence can be evaluated as described in Eq. (2). Here, the space boundary is considered as the summation of the Euclidean distance of all the members. ...
Electronic mails (emails) have been widely adapted by organizations and individuals as efficient communication means. Despite the pervasiveness of alternate means like social networks, mobile SMS, electronic messages, etc. email users are continuously growing. The higher user growth attracts more spammers who send unsolicited emails to anonymous users. These spam emails may contain malware, misleading information, phishing links, etc. that can imperil the privacy of benign users. The paper proposes a self-adaptive hybrid algorithm of big bang–big crunch (BB–BC) with ant colony optimization (ACO) for email spam detection. The BB–BC algorithm is based on the physics-inspired evolution theory of the universe, and the collective interaction behavior of ants is the inspiration for the ACO algorithm. Here, the ant miner plus (AMP) variant of the ACO algorithm is adapted, a data mining variant efficient for the classification. The proposed hybrid algorithm (HB ³ C-AMP) adapts the attributes of B ³ C (BB–BC) for local exploitation and AMP for global exploration. It evaluates the center of mass along with the consideration of pheromone value evaluated by the best ants to detect email spam efficiently. The experiments for the proposed HB ³ C-AMP algorithm are conducted with the Ling Spam and CSDMC2010 datasets. Different experiments are conducted to determine the significance of the pre-processing modules, iterations, and population size on the proposed algorithm. The results are also evaluated for the AM (ant miner), AM2 (ant miner2), AM3 (ant miner3), and AMP algorithms. The performance comparison demonstrates that the proposed HB ³ C-AMP algorithm is superior to the other techniques.
... Image position of the artificial light point j at iteration t. to control other lower-level wolves as well [26,27]. ...
Today, with the developing technology, access methods to information have also changed. Internet blogs and news sites, social media, etc. replace the traditional information access tools such as TV, radio, newspaper, and magazines. Cheaper and faster access than traditional methods and easy access from anywhere where the internet is available are the main factors in changing the access method to information. Besides, information spreads rapidly on the internet without proving the accuracy. There may be many reasons for the distribution of misinformation in this way, such as commercial, political, and economic. Information with fake content and deception purposes negatively affects both the person and the society. It is extremely important to detect deceptive information in textual data and researchers continue to propose new models in order to obtain efficient results in terms of many metrics. This paper proposes a new approach for deception detection problems. The deception detection problem was considered an optimization problem for the first time. Optics Inspired Optimization (OIO), Grey Wolf Optimization (GWO), and Chaos Based Optics Inspired Optimization (CBOIOs) are adapted and modeled for the first time in the deception detection problem. Deception detection models proposed in this article include data preprocessing, adapting optimization methods, and testing stages. An experimental evaluation and comparison of the proposed model and seven supervised machine learning algorithms are performed within two different data sets depending on four evaluation metrics (Accuracy, Recall, Precision, and F-Measure). Results show that CBOIOs are more effective than OIO, GWO, and other machine learning algorithms for this problem.
... Therefore, SN analysis methods can be used to determine the centrality or importance of each DM [34][35][36][37]. Additionally, the weight of each DM participating in the decision-making process can be determined to improve the accuracy of this process [38][39][40]. However, most of existing LSGDM methods cannot consider the incompleteness of relationships and consensus among DMs in an SN, which could render these methods ineffective when addressing actual decision-making problems. ...
Traditional large-scale group decision-making (LSGDM) methods assume that the decision-makers (DMs) are independent, and the trust relationships among DMs in the social network (SN) are complete. However, DMs always influence each other, and practical trust relationships among DMs in the SN are often incomplete. In this study, we propose a picture fuzzy LSGDM approach in a trust-relationship-based SN environment to solve decision-making problems. To achieve this, the incomplete trust relationship of SNs was considered first and the missing information was estimated using a picture fuzzy trust propagation operator. Next, a novel picture fuzzy Jensen a-norm dissimilarity measure was defined and the corresponding consensus detection model was developed for LSGDM in a trust-relationship-based SN environment. Afterward, based on the technique for order of preference by similarity to ideal solution (TOPSIS) approach, a picture fuzzy dissimilarity-based selection method was proposed for the selection process. Finally, two case studies were provided to demonstrate the effectiveness of the proposed approach. The sensitivity and comparison analyses demonstrated the stability and reliability of the decision-making results obtained using this method.
... Three years later, in 2020, this number reached 3 billion people. This number is expected to reach 4.41 billion people in 2025 (Can and Alatas, 2021a). Considering the large number of nodes in these networks and the edges between them, it is clear that these networks offer great opportunities for new research. ...
Abstract
Turkey as a country has a unitary state structure, which is managed as the capital city Ankara,
which consists of 81 city centers. Cities are hierarchically composed of districts, towns and
villages. Cities are areas with a certain population community. The areas with this population
community are in transportation, health, education, etc. Institutions were established in cities
to meet their needs. Municipalities, which are the local administrations of the cities, have been
made responsible for the design of all infrastructure and superstructure equipment, especially
the need for flourishing and housing of the cities. Municipalities sometimes carry out
infrastructure and superstructure improvement works in coordination with institutions such as
highways, state water works, and ilbank. Residential, commercial etc. In order to create the
necessary equipment in the city, the municipality has been given the authority to make the
implementation development plans in line with the master plans of the ministry. With this
authority, zoning plans were made in cities and revised according to needs. Zoning plans are
the plans in which all kinds of planning are made, from housing to transportation, from trade
to parks, from entertainment centers to social reinforcement areas of a city. In line with these
plans, the necessity of laying natural gas pipelines, which are infrastructure services, in a city
center was examined. As a method, it was discussed that just as the axons and dendrites in the
living body and brain nerve cells perform all kinds of movements with each other in the form
of a network, it is possible to design this type of natural gas lines by designing an artificial
network in the form of establishing main and intermediate distribution points. It was observed
that the main distribution points of the lines should be shown outside the settlements with a
certain legend within the zoning boundaries, and it was examined that the intermediate points
would be healthy if the areas such as green areas but not parks, such as electrical transformer
areas, were within a certain meter distance. The necessity of applying the lines in the form of
a network design by passing the lines under the ground by creating a certain level, digitizing
with the connection points and giving the coordinates was examined. In this way, in designing
a healthy network, it was determined that which point can be reached quickly and easily in
case of a malfunction, and that the possibility of living things to be affected will be at the
minimum level when these lines are passed in the light of a certain distance in case of an
explosion. The package program Basarisoft was used in the creation of natural gas lines.
These types of programs are geographic information system formations that are used to
digitize and integrate zoning plans and lines, and to store this network design in a computer
environment, minimizing time for formation and intervention.
Keywords: Zoning plan, city, natural gas, artificial neural networks
Purpose
In this paper, community identification has been considered as the most critical task of social network analysis. The purpose of this paper is to organize the nodes of a given network graph into distinct clusters or known communities. These clusters will therefore form the different communities available within the social network graph.
Design/methodology/approach
To date, numerous methods have been developed to detect communities in social networks through graph clustering techniques. The k-means algorithm stands out as one of the most well-known graph clustering algorithms, celebrated for its straightforward implementation and rapid processing. However, it has a serious drawback because it is insensitive to initial conditions and always settles on local optima rather than finding the global optimum. More recently, clustering algorithms that use a reciprocal KNN (k-nearest neighbors) graph have been used for data clustering. It skillfully overcomes many major shortcomings of k-means algorithms, especially about the selection of the initial centers of clusters. However, it does face its own challenge: sensitivity to the choice of the neighborhood size parameter k, which is crucial for selecting the nearest neighbors during the clustering process. In this design, the Jaya optimization method is used to select the K parameter in the KNN method.
Findings
The experiment on real-world network data results show that the proposed approach significantly improves the accuracy of methods in community detection in social networks. On the other hand, it seems to offer some potential for discovering a more refined hierarchy in social networks and thus becomes a useful tool in the analysis of social networks.
Originality/value
This paper introduces an enhancement to the KNN graph-based clustering method by proposing a local average vector method for selecting the optimal neighborhood size parameter k. Furthermore, it presents an improved Jaya algorithm with KNN graph-based clustering for more effective community detection in social network graphs.
Detecting communities in real and complex networks is a highly contested topic in network analysis. Although many metaheuristic-based algorithms for community detection have been proposed, they still cannot effectively fulfill large-scale and real-world networks. Thus, this paper presents a new discrete version of the Improved Grey Wolf Optimizer (I-GWO) algorithm named DI-GWOCD for effectively detecting communities of different networks. In the proposed DI-GWOCD algorithm, I-GWO is first armed using a local search strategy to discover and improve nodes placed in improper communities and increase its ability to search for a better solution. Then a novel Binary Distance Vector (BDV) is introduced to calculate the wolves’ distances and adapt I-GWO for solving the discrete community detection problem. The performance of the proposed DI-GWOCD was evaluated in terms of modularity, NMI, and the number of detected communities conducted by some well-known real-world network datasets. The experimental results were compared with the state-of-the-art algorithms and statistically analyzed using the Friedman and Wilcoxon tests. The comparison and the statistical analysis show that the proposed DI-GWOCD can detect the communities with higher quality than other comparative algorithms.
Stance detection improves fake information recognition in social media. This task encourages interpreting and explaining the misinformation identification, thus aligning with the importance of improving human trust in classification results. Nonetheless, most of the stance detection studies do not engage in understanding the reasons behind a solution. We propose a two-phase classification system for stance detection in tweets. We mainly exploit topic modeling features. Our proposal is remarkably different from previous ones since we provide an explanation of stance labels through the most relevant terms within topics over the tweets. Therefore, our approach is flexible because it adjusts to the vocabulary leveraging topic information. We additionally construct sets of features seeking tweet-specific content, sentiment and subjectivity markups, target attributes, term distribution, and word embeddings. Our classification system ranks second in the state-of-the-art regarding SemEval-2016 task 6 dataset with a 74.63% overall F-measure. To the best of our knowledge, our results are superior to deep learning-based proposals and competitive with studies that do not provide an explanation for stance labels. Hence, we affirm that topic modeling features enhanced classification results and provided textual information about a plausible explanation of stance labels. We report the performance of our system considering variations in the feature set, besides discussing the explanation of the results.
Stance detection (also known as stance classification, stance prediction, and stance analysis) is a problem related to social media analysis, natural language processing, and information retrieval, which aims to determine the position of a person from a piece of text they produce, towards a target (a concept, idea, event, etc.) either explicitly specified in the text, or implied only. Common stance classes include Favor, Against, and None. In this tutorial, we will define the core concepts and other related research problems, present historical and contemporary approaches to stance detection (including shared tasks and tools employed), provide pointers to related datasets, and cover open research directions and application areas of stance detection. As solutions to stance detection can contribute to diverse applications including trend analysis, opinion surveys, user reviews, personalization, and predictions for referendums and elections, it will continue to stand as an important research problem, mostly on textual content currently, and particularly on Web content including social media.
Stance detection (also known as stance classification and stance prediction) is a problem related to social media analysis, natural language processing, and information retrieval, which aims to determine the position of a person from a piece of text they produce, towards a target (a concept, idea, event, etc.) either explicitly specified in the text, or implied only. The output of the stance detection procedure is usually from this set: Favor, Against, None. In this tutorial, we will define the core concepts and research problems related to stance detection, present historical and contemporary approaches to stance detection, provide pointers to related resources (datasets and tools), and we will cover outstanding issues and application areas of stance detection. As solutions to stance detection can contribute to significant tasks including trend analysis, opinion surveys, user reviews, personalization, and predictions for referendums and elections, it will continue to stand as an important research problem, mostly on textual content currently, and particularly on social media. Finally, we believe that image and video content will commonly be the subject of stance detection research soon.
One may express favor (or disfavor) towards a target by using positive or negative language. Here for the first time we present a dataset of tweets annotated for whether the tweeter is in favor of or against pre-chosen targets, as well as for sentiment. These targets may or may not be referred to in the tweets, and they may or may not be the target of opinion in the tweets. We develop a simple stance detection system that outperforms all 19 teams that participated in a recent shared task competition on the same dataset (SemEval-2016 Task #6). Additionally, access to both stance and sentiment annotations allows us to conduct several experiments to tease out their interactions. We show that while sentiment features are useful for stance classification, they alone are not sufficient. We also show the impacts of various features on detecting stance and sentiment, respectively.
It is important to have an accurate mathematical model of a proton exchange membrane fuel cell (PEMFC) for simulation and design a nalysis. Due to deficiency of manufacture information about the accurate value of parameters required for the modeling, it is necessary to identify these parameters. The proposed Hybrid Big Bang-Big Crunch (HBB-BC) optimization algorithm is a meta-heuristic optimization method in which PSO algorithm is used to make more useful Big Crunch phases in BB-BC optimization. In this work the Hybrid BB-BC optimization is proposed to identify the PEMFC parameters. The HBB-BC results are compared with GA, PSO and BB-BC results to study the usefulness of proposed optimization method and indicate the proposed method is an effective and reliable technique which can be applied to identify the model's parameters of PEMFC.
This work proposes a new meta-heuristic called Grey Wolf Optimizer (GWO) inspired by grey wolves (Canis lupus). The GWO algorithm mimics the leadership hierarchy and hunting mechanism of grey wolves in nature. Four types of grey wolves such as alpha, beta, delta, and omega are employed for simulating the leadership hierarchy. In addition, the three main steps of hunting, searching for prey, encircling prey, and attacking prey, are implemented. The algorithm is then benchmarked on 29 well-known test functions, and the results are verified by a comparative study with Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Differential Evolution (DE), Evolutionary Programming (EP), and Evolution Strategy (ES). The results show that the GWO algorithm is able to provide very competitive results compared to these well-known meta-heuristics. The paper also considers solving three classical engineering design problems (tension/compression spring, welded beam, and pressure vessel designs) and presents a real application of the proposed method in the field of optical engineering. The results of the classical engineering design problems and real application prove that the proposed algorithm is applicable to challenging problems with unknown search spaces.
A great amount of work has been made in biologically-inspired robotic systems on single and multiple animal behavior models. These studies have advanced the understandings of animal behavior and have provided at the same time inspiration in the design of single and multiple robotic architectures. Additionally, applications in the real word domain have benefited from such work, like exploration, surveillance, etc. In this work we present a multi-robot architecture based on wolf packs studies showing different formations during prey hunting and predator avoidance. The model has been developed and tested using the NSL/ASL, MIRO systems, and Sony AIBO robots. Results from real robot experimentation are discussed
This work explores the utility of sentiment and arguing opinions for classifying stances in ideological debates. In order to capture arguing opinions in ideological stance taking, we construct an arguing lexicon automatically from a manually annotated corpus. We build supervised systems employing sentiment and arguing opinions and their targets as features. Our systems perform substantially better than a distribution-based baseline. Additionally, by employing both types of opinion features, we are able to perform better than a unigram-based system.
We propose a method for the task of identifying the general positions of users in online debates, i.e., support or oppose the main topic of an online debate, by exploiting local information in their remarks within the debate. An online debate is a forum where each user post an opinion on a particular topic while other users state their positions by posting their remarks within the debate. The supporting or opposing remarks are made by directly replying to the opinion, or indirectly to other remarks (to express local agreement or disagreement), which makes the task of identifying users' general positions difficult. A prior study has shown that a link-based method, which completely ignores the content of the remarks, can achieve higher accuracy for the identification task than methods based solely on the contents of the remarks. In this paper, we show that utilizing the textual content of the remarks into the link-based method can yield higher accuracy in the identification task.
This paper presents an unsupervised opin- ion analysis method for debate-side clas- sification, i.e., recognizing which stance a person is taking in an online debate. In order to handle the complexities of this genre, we mine the web to learn associa- tions that are indicative of opinion stances in debates. We combine this knowledge with discourse information, and formu- late the debate side classification task as an Integer Linear Programming problem. Our results show that our method is sub- stantially better than challenging baseline methods.
Stance detection is an important research direction which attempts to automatically determine the attitude (positive, negative, or neutral) of the author of text (such as tweets), towards a target. Nowadays, a number of frameworks have been proposed using deep learning techniques that show promising results in application domains such as automatic speech recognition and computer vision, as well as natural language processing (NLP). This article shows a novel deep learning-based fast stance detection framework in bipolar affinities on Twitter. It is noted that millions of tweets regarding Clinton and Trump were produced per day on Twitter during the 2016 United States presidential election campaign, and thus it is used as a test use case because of its significant and unique counter-factual properties. In addition, stance detection can be utilized to imply the political tendency of the general public. Experimental results show that the proposed framework achieves high accuracy results when compared to several existing stance detection methods.
The widespread use of Online Social Networks has also involved the scientific field in which researchers interact each other by publishing or citing a given paper. The huge amount of information about scientific research documents has been described through the term Big Scholarly Data. In this paper we propose a framework, namely Discovery Information using COmmunity detection (DICO), for identifying overlapped communities of authors from Big Scholarly Data by modeling authors' interactions through a novel graph-based data model combining jointly document metadata with semantic information. In particular, DICO presents three distinctive characteristics:i) the co-authorship network has been built from publication records using a novel approach for estimating relationships weight between users;ii) a new community detection algorithm based on Node Location Analysis has been developed to identify overlapped communities;iii) some built-in queries are provided to browse the generated network, though any graph-traversal query can be implemented through the Cypher query language. The experimental evaluation has been carried out to evaluate the efficacy of the proposed community detection algorithm on benchmark networks.Finally, DICO has been tested on a real-world Big Scholarly Dataset to show its usefulness working on the DBLP+AMiner dataset, that contains 1.7M+ distinct authors, 3M+ papers, handling 25M+ citation relationships.
In this paper we describe a novel algorithm based on Game Theory for Community Detection in Online Social Networks. Extending several Game Theoretic approaches that are well established in the literature, we propose a novel algorithm that outperforms the previous ones in terms of computational complexity and efficiency of results, as proved by a number of experiments on standard data sets.
Stance detection is the task of determining the perspective “or stance” of pairs of text. Classifying the stance (e.g. agree, disagree, discuss or unrelated) expressed in news articles with respect to a certain claim is an important step in detecting fake news. Many neural and traditional models predict well on unrelated and discuss classes while they poorly perform on other minority represented classes in the Fake News Challenge-1 (FNC-1) dataset. We present a simple neural model that combines similarity and statistical features through a MLP network for news-stance detection. Aiding augmented training instances to overcome the data imbalance problem and adding batch-normalization and gaussian-noise layers enable the model to prevent overfitting and improve class-wise and overall accuracy. We also conduct additional experiments with a light-GBM and MLP network using the same features and text augmentation to show their effectiveness. In addition, we evaluate the proposed model on the Argument Reasoning Comprehension (ARC) dataset to assess the generalizability of the model. The experimental results of our models outperform the current state-of-the-art.
The use of online social networks has made significant progress in recent years as the use of the Internet has become widespread worldwide as the technological infrastructure and the use of technological products evolve. It has become more suitable to reach online social networking sites such as Facebook, Twitter, Instagram and LinkedIn via the internet and web 3.0 technologies. Thus, people have shared their views on many different topics and their emotions with other users more widely on these platforms. This means that a huge amount of data is created on platforms where millions of people connect with each other through social networks. Nevertheless, the development of computational paradigms at high speed and complexity with technological possibilities allows analysis of valuable data by means of social network analysis methods. Our goal for this paper is to present a review of novel and popular online social network analysis problems with related applications and a reference work for researchers interested in analyzing online social network data and social network problems. Unlike other individual studies we have gathered 21 online social network problems and defined them with related studies. Thus, this study is original by presenting an important source of research by explaining the problems of online social network and the studies performed in this area.
The traditional projection models in the bipartite networks involve many node pairs that consist of weak relationships. These node pairs lead to poor quality predictions as well as high computation time. In this paper, to cope with these problems, we firstly propose a novel projection model, which is called “Strengthened Projection Model”. Then, to predict the potential links in the future, we present a new link prediction approach based on the proposed projection model. Thanks to the proposed model, the computation time is shortened, and the high probability predictions are extracted. The majority of the previous works conducted in this area have used the classical proximity measure algorithms that only take into account the current network structure, regardless of when events occur in the network evolution. To overcome these limited methods, in this paper, we also propose a novel proximity measure algorithm that considers the bipartite network evolution. To the best of our knowledge, this is the first attempt that takes into account the time-awareness in bipartite networks. To evaluate the performance of our proposed approach, we conducted experiments on the academic information network. To construct this bipartite network, we collected data from IEEE Xplore. The experimental results show that the success of the proposed method is promising.
With rapid emergence of online social networks, the rumor transition has a growing significant impact on social stability and human lives. This paper investigates the local stability and optimal control of a rumor propagation model in online social network with changing number of total users, which is proposed in Ref. Dong et al. (2018). In addition, we set up a model with a delay based on the reality, and analyze the sufficient conditions for Hopf bifurcation. Finally, the rumor spreading model is simulated numerically. The results of simulation are shown the process of rumor propagation and prove the correctness of the theoretical analysis.
Stance detection is an important research direction which attempts to automatically determine the attitude (positive, negative, or neutral) of the author of text (such as tweets), towards a target. Nowadays, a number of frameworks have been proposed using deep learning techniques that show promising results in application domains such as automatic speech recognition and computer vision, as well as natural language processing (NLP). This article shows a novel deep learning-based fast stance detection framework in bipolar affinities on Twitter. It is noted that millions of tweets regarding Clinton and Trump were produced per day on Twitter during the 2016 United States presidential election campaign, and thus it is used as a test use case because of its significant and unique counter-factual properties. In addition, stance detection can be utilized to imply the political tendency of the general public. Experimental results show that the proposed framework achieves high accuracy results when compared to several existing stance detection methods.
Among internet and smart device applications, Twitter has become a leading social media platform, disseminating online events occurring in the world on a real-time basis. Many studies have been conducted to identify valuable information on Twitter. Recently, Frequent Pattern Mining has been applied for topic detection on Twitter. In Frequent Pattern Mining, a topic is considered to be a group of words that appear simultaneously, however, the method only considers the frequency of words, and their utility for topic detection is not considered in the process of pattern generation. In this paper, we propose a method to detect emerging topics on Twitter based on High Utility Pattern Mining (HUPM), which takes frequency and utility into account at the same time. For a chunk of tweets by time-based windowing on the Twitter stream, we define the utility of words based on the growth rate in frequency and find groups of words with high frequency and high utility by HUPM. For post-processing to extract actual topic patterns from candidate topic patterns generated by HUPM, an efficient data structure called Topic-tree (TP-Tree) is also proposed. Experimental results demonstrated the effectiveness of the proposed method, which showed superior performance and shorter running time than other tested topic detection methods. In particular, the proposed method showed a 5% higher topic recall than the other compared methods for the three datasets used.
In recent years, data on the Internet has grown exponentially, attaining enormous dimensions. This situation makes it difficult to obtain useful information from such data. Web mining is the process of using data mining techniques such as association rules, classification, clustering, and statistics to discover and extract information from Web documents. Optimization algorithms play an important role in such techniques. In this work, the parliamentary optimization algorithm (POA), which is one of the latest social-based metaheuristic algorithms, has been adopted for Web page classification. Two different data sets (Course and Student) were selected for experimental evaluation, and HTML tags were used as features. The data sets were tested using different classification algorithms implemented in WEKA, and the results were compared with those of the POA. The POA was found to yield promising results compared to the other algorithms. This study is the first to propose the POA for effective Web page classification.
Online debate sites are a large source of informal and opinion-sharing dialogue on current socio-political issues. Inferring users’ stance (PRO or CON) towards discussion topics in domains such as politics or news is an important problem, and is of utility to researchers, government organizations, and companies. Predicting users’ stance supports identification of social and political groups, building of better recommender systems, and personalization of users’ information preferences to their ideological beliefs. In this paper, we develop a novel collective classification approach to stance classification, which makes use of both structural and linguistic features, and which collectively labels the posts’ stance across a network of the users’ posts. We identify both linguistic features of the posts and features that capture the underlying relationships between posts and users. We use probabilistic soft logic (PSL) (Bach et al., 2013) to model post stance by leveraging both these local linguistic features as well as the observed network structure of the posts to reason over the dataset. We evaluate our approach on 4FORUMS (Walker et al., 2012b), a collection of discussions from an online debate site on issues ranging from gun control to gay marriage. We show that our collective classification model is able to easily incorporate rich, relational information and outperforms a local model which uses only linguistic information.
This paper proposes a novel nature-inspired meta-heuristic optimization algorithm, called Whale Optimization Algorithm (WOA), which mimics the social behavior of humpback whales. The algorithm is inspired by the bubble-net hunting strategy. WOA is tested with 29 mathematical optimization problems and 6 structural design problems. Optimization results prove that the WOA algorithm is very competitive compared to the state-of-art meta-heuristic algorithms as well as conventional methods. The source codes of the WOA algorithm are publicly available at http://www.alimirjalili.com/WOA.html.
Entries in microblogging sites are very short. For example, a 'tweet' (a post or status update on the popular microblogging site Twitter) can contain at most 140 characters. To comply with this restriction, users frequently use abbreviations to express their thoughts, thus producing sentences that are often poorly structured or ungrammatical. As a result, it becomes a challenge to come up with methods for automatically identifying named entities (names of persons, organizations, locations etc.). In this study, we use a four-step approach to automatic named entity recognition from microposts. First, we do some preprocessing of the micropost (e.g. replace abbreviations with actual words). Then we use an off-the-shelf part-of-speech tagger to tag the nouns. Next, we use the Google Search API to retrieve sentences containing the tagged nouns. Finally, we run a standard Named Entity Recognizer (NER) on the retrieved sentences. The tagged nouns are returned along with the tags assigned by the NER. This simple approach, using readily available components, yields promising results on standard benchmark data.
This chapter discusses the characteristics, taxonomy, distribution, abundance, and ecology of the humpback whale or Megaptera novaeangliae. The humpback whale is one of the best known and easily recognizable of the large whales. It is known for its frequent acrobatic behavior and its occasional tendency to approach vessels. At close range, humpback whales are easily distinguished from any other large whale by their remarkably long flippers, which are approximately one-third the length of the body. The flippers are ventrally white and can be either white or black dorsally depending on the population and the individual; the flippers of North Atlantic humpbacks tend to be white, while those in the North Pacific are usually black. Humpback whales are found in all oceans of the world. They are a highly migratory species, spending spring through fall on feeding grounds in mid- or high-latitude waters, and wintering on calving grounds in the tropics, where they do not eat. They are typically found in coastal or shelf waters in summer and close to islands or reef systems in winter. The humpback whale is heavily exploited by the whaling industry for several centuries. Because of its coastal distribution, it is often the first species to be hunted in a newly discovered area. As a result, the humpback is considered as an endangered species.
Online debate forums present a valuable opportunity for the understanding and modeling of dialogue. To understand these debates, a key challenge is inferring the stances of the participants, all of which are interrelated and dependent. While collectively modeling users' stances has been shown to be effective (Walker et al., 2012c; Hasan and Ng, 2013), there are many modeling decisions whose ramifications are not well understood. To investigate these choices and their effects, we introduce a scalable unified probabilistic modeling framework for stance classification models that 1) are collective, 2) reason about disagreement, and 3) can model stance at either the author level or at the post level. We comprehensively evaluate the possible modeling choices on eight topics across two online debate corpora, finding accuracy improvements of up to 11.5 percentage points over a local classifier. Our results highlight the importance of making the correct modeling choices for online dialogues, and having a unified probabilistic modeling framework that makes this possible.
Clustering of text documents enables unsupervised categorization and facilitates browsing and search. Any clustering method has to embed the objects to be clustered in a suitable representational space that provides a measure of (dis)similarity between any pair of objects. While several clustering methods and the associated similarity measures have been proposed in the past for text clus-tering, there is no systematic comparative study of the impact of similarity mea-sures on the quality of document clusters, possibly because most popular cost criteria for evaluating cluster quality do not readily translate across qualitatively different measures. This chapter compares popular similarity measures (Euclidean, cosine, Pearson correlation, extended Jaccard) in conjunction with several clustering techniques (random, self-organizing feature map, hypergraph partitioning, general-ized k-means, weighted graph partitioning), on a variety of high dimension sparse vector data sets representing text documents as bags of words. Performance is measured based on mutual information with a human-imposed classification. Our key findings are that in the quasiorthogonal space of word frequencies: (i) Cosine, correlation, and extended Jaccard similarities perform comparably; (ii) Euclidean distances do not work well; (iii) Graph partitioning tends to be superior espe-cially when balanced clusters are desired; (iv) Performance curves generally do not cross.
A growing body of work has highlighted the challenges of identifying the stance that a speaker holds towards a particular topic, a task that involves identifying a holistic subjective disposition. We examine stance classification on a corpus of 4731 posts from the debate website ConvinceMe.net, for 14 topics ranging from the playful to the ideological. We show that ideological debates feature a greater share of rebuttal posts, and that rebuttal posts are significantly harder to classify for stance, for both humans and trained classifiers. We also demonstrate that the number of subjective expressions varies across debates, a fact correlated with the performance of systems sensitive to sentiment-bearing terms. We present results for classifying stance on a per topic basis that range from 60% to 75%, as compared to unigram baselines that vary between 47% and 66%. Our results suggest that features and methods that take into account the dialogic context of such posts improve accuracy.
The prevailing view of a wolf (Canis lupus) pack is that of a group of individuals ever vying for dominance but held in check by the 'alpha' pair, the alpha male and alpha female. Most research on the social dynamics of wolf packs, however, has been conducted on non-natural assortments of captive wolves. Here I describe the wolf-pack social order as it occurs in nature, discuss the alpha concept and social dominance and submission, and present data on the precise relationships among members in free-living packs, based on a literature review and 13 summers of observations of wolves on Ellesmere Island, Northwest Territories, Canada. I conclude that the typical wolf pack is a family, with the adult parents guiding the activities of the group in a division-of-labor system in which the female predominates primarily in such activities as pup care and defense and the male primarily during foraging and food-provisioning and the travels associated with them.
In this paper we propose a novel measure based on the earth mover’s distance (EMD) to evaluate document similarity by allowing many-to-many matching between subtopics. First, each document is decomposed into a set of subtopics, and then the EMD is employed to evaluate the similarity between two sets of subtopics for two documents by solving the transportation problem. The proposed measure is an improvement of the previous OM-based measure, which allows only one-to-one matching between subtopics. Experiments have been performed on the TDT3 dataset to evaluate existing similarity measures and the results show that the EMD-based measure outperforms the optimal matching (OM) based measure and all other measures. In addition to the TextTiling algorithm, the sentence clustering algorithm is adopted for document decomposition, and the experimental results show that the proposed EMD-based measure does not rely on the document decomposition algorithm and thus it is more robust than the OM-based measure.
Nature is the principal source for proposing new optimization methods such as genetic algorithms (GA) and simulated annealing (SA) methods. All traditional evolutionary algorithms are heuristic population-based search procedures that incorporate random variation and selection. The main contribution of this study is that it proposes a novel optimization method that relies on one of the theories of the evolution of the universe; namely, the Big Bang and Big Crunch Theory. In the Big Bang phase, energy dissipation produces disorder and randomness is the main feature of this phase; whereas, in the Big Crunch phase, randomly distributed particles are drawn into an order. Inspired by this theory, an optimization algorithm is constructed, which will be called the Big Bang-Big Crunch (BB-BC) method that generates random points in the Big Bang phase and shrinks those points to a single representative point via a center of mass or minimal cost approach in the Big Crunch phase. It is shown that the performance of the new (BB-BC) method demonstrates superiority over an improved and enhanced genetic search algorithm also developed by the authors of this study, and outperforms the classical genetic algorithm (GA) for many benchmark test functions.
We have produced computational simulations of multi-agent systems in which wolf agents chase prey agents. We show that two simple decentralized rules controlling the movement of each wolf are enough to reproduce the main features of the wolf-pack hunting behavior: tracking the prey, carrying out the pursuit, and encircling the prey until it stops moving. The rules are (1) move towards the prey until a minimum safe distance to the prey is reached, and (2) when close enough to the prey, move away from the other wolves that are close to the safe distance to the prey. The hunting agents are autonomous, interchangeable and indistinguishable; the only information each agent needs is the position of the other agents. Our results suggest that wolf-pack hunting is an emergent collective behavior which does not necessarily rely on the presence of effective communication between the individuals participating in the hunt, and that no hierarchy is needed in the group to achieve the task properly.
Social networking goes abroad
- Murray
K.E. Murray, R. Waller, Social networking goes abroad, Int. Educat. 16 (3) (2007)
56.
- K Darwish
- P Stefanov
- M J Aupetit
- P Nakov
K. Darwish, P. Stefanov, M.J. Aupetit, P. Nakov, Unsupervised User Stance
Detection on Twitter, 2019 arXiv preprint arXiv:1904.02000.
Stance classification of ideological debates: data, models, features, and constraints
- Hasan
K.S. Hasan, V. Ng, Stance classification of ideological debates: data, models,
features, and constraints, in: Proceedings of the Sixth International Joint
Conference on Natural Language Processing, Nagoya, Japan, 2013, pp. 14-18
(October).
A joint sentiment-target-stance model for stance classification in tweets
- J Ebrahimi
- D Dou
- D Lowd
J. Ebrahimi, D. Dou, D. Lowd, A joint sentiment-target-stance model for stance
classification in tweets, in: Proceedings of COLING 2016, the 26th International
Conference on Computational Linguistics: Technical Papers, Osaka, Japan,
December, 2016, pp. 11-17.
- D Küçük
- F Can
D. Küçük, F. Can, Stance Detection on Tweets: an SVM-Based Approach, 2018 arXiv
preprint arXiv:1803.08910.
Büyük Patlama–Büyük Çöküş Optimizasyon Yöntemi kullanılarak Bluetooth tabanlı İç mekan konum Belirleme sisteminin doğruluğunun İyileştirilmesi
- Arsan
T. Arsan, Büyük Patlama-Büyük Çöküş Optimizasyon Yöntemi kullanılarak
Bluetooth tabanlı İ ç mekan konum Belirleme sisteminin dogrulugunun
İ yileştirilmesi, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi 22
(2018) 367-374.
A joint sentiment-target-stance model for stance classification in tweets
- Ebrahimi