Web Log Analysis Research Articles

Web Attack Detection Based on Honeypots and Logistic Regression Algorithm

Web security has emerged as one of the most prominent concerns in the realm of cybersecurity. Traditional rule-based methods for detecting web attacks often rely on manual rule definition and pattern matching, leaving them inadequate in accurately identifying new and intricate attack patterns. In the face of these challenges, machine learning techniques have demonstrated potential and advantages. This paper presents a web attack detection method based on honeypots and the logistic regression algorithm. It involves the cleansing, filtering, and analysis of web logs captured by honeypots, followed by the vectorization of the textual data contained in these logs. The logistic regression algorithm is employed to train and test the classification of the text vectors, generating a logistic regression model. This model is then used to predict newly generated web logs, enabling effective dynamic web attack detection. Experimental evaluations using collected datasets are conducted, comparing the proposed method with the support vector machine approach. The results demonstrate that this method achieves rapid and accurate detection and recognition of web attack behaviors while ensuring performance efficacy.

The Path of Least Resistance: Optimizing Metadata Practices through User Assessment

As part of a multi-faceted research project examining user engagement with various types of descriptive metadata to improve metadata services, Utah State University Libraries Cataloging and Metadata Services unit investigated user search behavior in library catalog (MARC) records, Encoded Archival Description (EAD) finding aids, and most recently in digital collection metadata. The authors used web log analysis to determine how users interacted with CONTENTdm, categories of search terms used, and where search terms were found in a record. Key findings included that navigation through CONTENTdm using clickable queries (links) is a prominent user search pattern, dates are an important faceting tool and date ranges as a clickable link are heavily used, users demonstrated a more engaged research pattern when searching with geographic terms, and subject and transcription metadata fields match user search terms at a significant rate and are likely to be high drivers of search results.

Identity engineering of post-Yugoslav countercultural transculturalism

The subject of the paper is post-Yugoslav countercultural identity engineering as an ideological construct of left-liberal Euro-Atlantic totalitarianism. The author studies the subject through the analysis of a model of countercultural action directed against the basic identifiers of Serbian cultural identity - Svetosavlje as the Othodox Cristians philosophy of life derived from the teaching of Saint Sava, whose spiritual creation is a centuries-oldvalue system, and the Cyrillic script of the Serbian language through which the Serbian people communicate the Saint Sava worldview. The aim of the research is to understand and explain the way of thinking and action of neoliberal Euro-Atlantic totalitarianism in the area of the former Yugoslavia based on theoretical sources, analysis of empirical data, media texts, internet presentations and weblogs. The results of the historical-comparative analysis of Yugoslav and post-Yugoslav identity engineering show that a key role in the process is played by the hybrid model ?double of the state? which assumes the role of a cultural hegemon. Model operates on the principle of ?divide and rule? by antagonizing existing political and cultural identities to impose a set of beliefs about gender identity with devastating consequences for society as a whole. For expansion of left-liberal Euro-Atlantic totalitarianism to the poscommunist Europe after the breakup of Yugoslavia, the ?double of the state? model was necessary in order to remove all the subversive contents of cultural identity. This especially refers to the key identifiers of the Serbian cultural identity, which the comunist - ateist ideology of Yugoslavia perceived as a threat due to the alleged ?Greater Serbian hegemony and nationalism?, and has already pushed it out of public life to a significant extent. Thus, the post -Yugoslav left-liberal ideology found its natural ally in neoliberal Euro-Atlantic countercultural transculturalism.

Using web log analysis to evaluate healthcare students' engagement behaviours with multimedia lectures on YouTube.

The objective of this study was to utilise web log analysis to evaluate the relationship between University students' engagement (e.g., watch time) and the characteristics of a catalogue of multimedia lectures, including their duration, the speaking rate of the narrator and the extent to which they implemented certain principles from Mayer's Cognitive Theory of Multimedia Learning (CTML). Fifty-six multimedia lectures covering topics related to healthcare (e.g., anatomy, physiology and clinical assessment) were developed to differentially employ the image/embodiment, redundancy, segmentation and signalling principles from the CTML. These lectures were delivered to multiple cohorts of students throughout an academic semester. Student watch time was evaluated using the meta-usage data provided by YouTube studio. The multimedia lectures were viewed 4338 times (mean = 35 views per lecture; 27 unique viewers per lecture). Generalised estimating equations revealed that videos that were segmented into shorter chunks, that incorporated signals to highlight important information for students and during which captions were toggled 'off' by students were associated with longer watch times (P < 0.05). Additionally, watch time diminished for videos placed later in a sequence based on the audience retention metric. When designing multimedia lectures, instructors should be encouraged to use on screen labels to highlight important information, segment learning material into shorter 'chunks' and incorporate a dynamic instructor on screen at regular intervals displaying high embodiment. If several videos are to be delivered to students as part of a learning 'unit', educators should consider placing the most important learning material earlier in the sequence.

Pelatihan Web Log Sebagai Media Publikasi Sekolah dan Kegiatan Belajar Mengajar di SDN 1 Ngampel

The pandemic makes the utilization and competition of information and communication technology has increased. One of the ways to maintain the existence of schools are publication media of more varied school information and teaching-learning activities media. The purpose of this training program is to provide additional expertise for creating inexpensive and fast publications media and teaching-learning media. The offered solution is the use of web logs from Google which is often known as Blogger. Blogger offers a free and easy web log feature. The training was carried out directly at the Sekolah Dasar Negeri 1 Ngampel by using lectures and demonstrations method. There are several parts in this training, web log making, web log management, and also web log analysis. The results of this training show that the participants have succeeded in having their own web logs which are ready to be further managed and analyzed on a regular basis. The use of web logs can be used for various needs, including as a publication media and supporting teaching-learning activities.

Web Log Analysis and Security Assessment Method Based on Data Mining.

Web content mining describes the classification, clustering, and attribute analysis of a large number of text documents and multimedia files on the web. Special tasks include retrieval of data from the Internet search engine tool W; structured processing and analysis of web data. Today's blog analysis has security concerns. We do experiments to investigate its safety. Through experiments, we draw the following conclusions: (1) Web log extraction can use efficient data mining algorithms to systematically extract logs from web servers, then determine the main access types or interests of users, and then to a certain extent, based on the discovered user patterns, analyze the user's access settings and behavior. (2) No matter in the test set or the mixed test set, the curve value of deep mining is very stable, the curve value has been kept at 0.95, and the curve value of fuzzy statistics method and quantitative statistics method is stable within the interval of 0.90-095. The results also show that the data mining method has the highest identification accuracy and the best security performance. (3) Web usage analysis requires data abstraction for pattern discovery. This data abstraction can be achieved through data preprocessing, which introduces different formats of web server log files and how web server log data is preprocessed for web usage analysis. One of the most critical parts of the web mining field is web log mining. Web log mining can use powerful data mining algorithms to systematically mine the logs in the web server and then learn the user's access or preferred interests and then conduct a certain degree of user preferences and behavior patterns according to the discovered user patterns. Based on the above analysis, the current web log analysis is faced with security problems. We conduct experiments to study to verify the security performance of web logs and draw conclusions through experiments.

An investigation into the relationship between multimedia lecture design and learners' engagement behaviours using web log analysis.

The purpose of this transaction log analysis was to evaluate university students' engagement behaviours with a catalogue of multimedia lectures. These lectures incorporated selected instructional design principles from the cognitive theory of multimedia learning (CTML). Specifically, thirty-two multimedia lectures which differentially employed the signalling, segmenting and embodiment principles from the CTML were delivered to a cohort of 92 students throughout an academic trimester. Engagement with each multimedia lecture was measured in three domains: affective engagement was measured using a Likert-style survey that accompanied each multimedia lecture; behavioural engagement was measured using the web logs provided by YouTube Studio analytics (average watch time); cognitive engagement was measured using students' average score on a quiz that accompanied each multimedia lecture. Separate multiple linear regression analyses for measures of affective, behavioural and cognitive engagement revealed that multimedia lectures that 'stacked' the instructional design principles of embodiment (whereby the lecture was interspersed with clips of an enthusiastic onscreen instructor), segmenting (where lectures were divided into shorter, user-paced segments) and signalling (where onscreen labels highlighted important material) increased measures of engagement, including overall watch time, number of survey submission and number of quiz attempts (P < 0.05). There was no association between any of the tested principles and students' quiz scores or their responses on the Likert-style survey. This study adds to the available literature demonstrating the effectiveness of the signalling, segmenting and embodiment principles for increasing learner engagement with multimedia lectures.

Internet Digital Economy Development Forecast Based on Artificial Intelligence and SVM-KNN Network Detection.

The development and spread of Internet technology have made it easier to find web servers. People can browse various websites to shop or pay for living expenses, which brings great convenience to life, but as a result, Internet security problems continue to appear. This article is based on a detailed theoretical analysis of mainstream algorithms, making an analysis of web logs which is of great significance and practical value. In addition, through reasoning analysis, technical support is provided for improving the weight factor of the KNN (K-nearest neighbor) algorithm, and the literature research method of the SVM-KNN hybrid algorithm and the KNN classifier is proposed. This paper conducts a detailed theoretical analysis based on the mainstream algorithms that are widely used in the current classification technology and integrates the mainstream classification algorithms in real-life applications and popularization, selecting the support vector machine and KNN calculation method. In the digital economy development model, although China has a large number of netizens, obvious late-comer advantages and institutional advantages as a guarantee, due to the constraints of two key factors, capital and technology, a series of social problems have also arisen. During the transformation of the digital economy, prominent digital security issues, high-risk vulnerabilities, and increasing number of cyber-attacks, along with uneven data quality levels and lagging laws and regulations, have brought many challenges and obstacles.

Web Server Analysis

Abstract: This is a design and implementation of a Web Server. “WEB SERVER ANALYSIS” is a software developed for managing log files on the server. Web log analysis is an innovative and unique field constantly formed and changed by the convergence of various emerging Web technologies. Due to its interdisciplinary character, the diversity of issues it addresses, and the variety and number of Web applications, it is the subject of many distinctive and diverse research methodologies. This project deals with the analysis of the log files of a web server. Keywords: Web server, Log files, Error, URL, Resources

Weblog Analysis for Predicting Correlations in Stock Price Evolutions

We use data extracted from many weblogs to identify the underlying relations of a set of companies in the Standard and Poor (S\&amp;P) 500 index. We define a pairwise similarity measure for the companies based on the weblog articles and then apply a graph clustering procedure. We show that it is possible to capture some interesting relations between companies using this method. As an application of this clustering procedure we propose a cluster-based portfolio selection method which combines information from the weblog data and historical stock prices. Through simulation experiments, we show that our method performs better (in terms of risk measures) than cluster-based portfolio strategies based on company sectors or historical stock prices. This suggests that the methodology has the potential to identify groups of companies whose stock prices are more likely to be correlated in the future.

WITHDRAWN: Web log analysis using Spark with solution recommendation

The robustness required by the web server that operates behind those giant service providers must be taken into account in today's world, where any service is accessible on the internet in the form of large sites or exceptional web applications. The businesses spend a great deal of money on maintaining these servers so that they work always at their highest level. The amount of data that is transacted and the intricacies involved in the Internet every microsecond is beyond man's imagination. The server needs to run 24X7 to make it easier for their demanding clients. Incidents, however, have contributed to millions of dollars losses for the organization due to a malfunction of a company server and it merely emphasizes the value of a stable server. Each server contains details about the requests that it has previously handled, called web server logs, and it is extremely valuable because it gives us information about the potential reasons for the server failure. For a certain period, famine attacks (DDOS attacks) and many others may be overloaded. The web server's audit logs include details about the response code it generates and should the error codes involved be well examined, the reasons for a server failure might probably be identified. We aim to review the error code documents to gain their information and evaluate web server logs using a solution-recommendation framework that informs the server administrator of the potential reasons for any previous server breakdowns and how it can be prevented. For analysis, we will be using Apache Spark keeping in mind its in-memory processing of data, making it a lot faster than Map Reduce of the Hadoop ecosystem which goes for batch processing.

Identifying the future direction of legal deposit in the United Kingdom: The Digital Library Futures approach

PurposeTo date, there has been little research into users of the Legal Deposit Libraries (Non-Print Works) Regulations 2013. This paper addresses that gap by presenting key findings from the AHRC-funded Digital Library Futures project. Its purpose is to present a “user-centric” perspective on the potential future impact of the digital collections that are being created under electronic legal deposit regulations.Design/methodology/approachThe study utilises a mixed methods case study of two academic legal deposit libraries in the United Kingdom: The Bodleian Libraries, University of Oxford; and Cambridge University Library. It combines surveys of users, web log analysis and expert interviews with librarians and cognate professionals.FindingsUser perspectives on NPLD were not fully considered in the planning and implementation of the 2013 regulations. The authors present findings from their user survey to show how contemporary tensions between user behaviour and access protocols risk limiting the instrumental value of NPLD collections, which have high perceived legacy value.Originality/valueThis is the first study to address the user context for UK Non-Print Legal Deposit. Its value lies in presenting a research-led user assessment of NPLD and in proposing “user-centric” analysis as an addition to the existing “four pillars” of legal deposit research.

Adaptive Drift Detection Mechanism for Non-Stationary Data Stream

Mining is a challenging and important task in a non-stationary data stream. It is used in financial sectors, web log analysis, sensor networks, network traffic management, etc. In this environment, data distribution may change overtime and is called concept drift. So, it is necessary to identify the changes and address them to keep the model relevant to the incoming data. Many researchers have used Drift Detection Method (DDM). However, DDM is very sensitive to detect gradual drift where the detection delay is high. In this paper, we propose Adaptive Drift Detection Method (ADDM) which improves the performance of the drift detection mechanism. The ADDM uses a new parameter to detect the gradual drift in order to reduce the detection delay. The proposed method, ADDM, experiments with six synthetic datasets and four real-world datasets. Experimental results confirm that ADDM reduces the drift detection delay and false-positive rate (FPR) while preserving high classification accuracy.

Predicting User’s Web Navigation behaviour using AMD and HMM Approaches

The academics were introducing various techniques in web usage mining to reduce user latency time to improve their web performance. The server-side web log data helps to identify the most appropriate pages, based on the user’s request. Analyzing web log data creates difficulties since it comprises exhaustive web page data. This paper proposes a new technique in which the web log data we can preprocess in order to extract sequence and navigation patterns useful to predict. In this paper, we cluster users into communities labelled by the websites most frequently visited, to discover their preferences and to describe website reorganisation. The URL sequence navigated by a user during a session. Session denotes a user’s browsing pattern. Multiple users’ sessions are clustered using the hierarchical clustering technique to analyse the sequence in their navigation patterns. The two model predictions are Adaptive Mahanabolis Distance (AMD) and Hidden Markov model (HMM), providing a list of web pages of interest to the user. We validate the proposed framework on NASA, Clarknet and serc datasets web log files.

Efficient Approach of Analyzing and Generating Intrinsic Information from Weblog

The weblog data have unstructured data, and due to this extraction, the desired information from it is a very challenging task. This kind of data is rapidly growing with huge volume. In this paper, the weblog analysis through Pyspark (WAP) algorithm is proposed to analyze the complete weblog dataset and extract useful information from it. In the proposed approach is used Resilient Distributed Dataset (RDD) for running and operating on multiple nodes to do parallel processing on a cluster; for achieving these concepts is used apache pyspark and implemented on jupyter notebook. WAP extracts different results such as host count, path count, status count, etc. This approach also generates patterns and track user behavior. The recommendation is also possible by the proposed algorithm based on user behaviors.

Research on Optimized Storage and Analysis System of Web Log Based on Django’s MVC Framework

Association rule analysis algorithm is widely used in Web log analysis, but the existing association rule analysis algorithm will significantly reduce the analysis and mining performance when the amount of Web log is relatively large. This paper proposes an improved clustering algorithm, which first clusters users with the same interests and hobbies, and then mines association rules for users in the same category, thereby reducing data dispersion. Based on Django’s MVC framework, it optimizes the storage and storage of Web logs. In the analysis part, users can configure the support and confidence of association rule mining through the front-end, and at the same time query the results of mining through Hive, and use encryption algorithms in the data transmission process to ensure data security.

Anytime Frequent Itemset Mining of Transactional Data Streams

Mining frequent itemsets from transactional data streams has become very essential in today's world with many applications such as stock market analysis, retail chain analysis, web log analysis, etc. Various algorithms have been proposed to efficiently mine single-port and multi-port transactional streams within the constraints of limited time and memory. However, all of them are budget algorithms, i.e., they are not capable of handling varying inter-arrival rate of transactions and high speed streams. They are constrained by a maximum limit to the inter-arrival rate of transactions, beyond which they fail to process. Also, these algorithms are not capable of giving immediate mining results, even with compromised accuracy if required. The above two properties characterize an anytime algorithm. We propose AnyFI, which is the first anytime frequent itemset mining algorithm for data streams. AnyFI uses a novel data structure - BFI-forest, which is capable of handling transactions arriving at variable rate. It maintains itemsets in BFI-forest in such a way that it can give a mining result almost immediately when the time allowance to mine is very less and can refine its accuracy with increase in time allowance. We also propose MPAnyFI which extends AnyFI into a parallel framework for anytime frequent itemset mining of multi-port data streams over commodity clusters. It uses AnyFI at each computing node of the cluster. Our extensive experimental analysis shows that AnyFI can handle high stream speeds close to 60,000 trans/sec with recall close to 100%. They also show the efficiency of MPAnyFI.

Web Log Analysis of a Digital Game-Based Learning System in Vocabulary Enrichment for College Students

Web Log Analysis of a Digital Game-Based Learning System in Vocabulary Enrichment for College Students

Fuzzy Integrated Ontology Model of Dynamic Learner Profiling

In the context of lifelong learning, learner profile has emerged as a feasible model that support and promote the provision of lifelong learning opportunities. Learner profile describes the attributes and outcomes of education in a learning system. It includes information on learner’s gender, skills, education, interest, learning preferences, learning style, etc. This paper proposes an approach to construct a fuzzy based semantic learner profile in the promising technology of semantic web by using the concept of ontology and use it for the reasoning of learner preferences. The approach starts with the collection of learner’s static and dynamic data. The dynamic data of learner particularly learner interest and learning style are extracted by weblog analysis and using algorithms such as semantic based representation using WordNet and modified decision tree classifier with strong rules based on Felder-Silverman learning style model. The retrieved data is then used to construct learner profile using ontology in which automatic learner profile updating is obtained using ontology based semantic similarity algorithm. Finally to achieve semantic retrieval from learner profile ontology, fuzzy concepts such as fuzzy linguistic variable and fuzzy IF THEN rules are applied. Fuzzy linguistic variable facilitate semantic retrieval and more specific classification from learner profile ontology and fuzzy IF THEN rules predict the learning preference of new students based on the forward chaining reasoning process implemented in the existing ontology model. The final representation of semantic fuzzy ontology based learner profile improves the performance of tasks such as classification, semantic retrieval and prediction of learning preference to the new learners. The case study is conducted for the real-time learners involved in studying the courses registered in Moodle Learning Management System. The experiments were performed with NetBeans IDE, Jena framework and Protégé 4.2 beta editor. The experiments confirm that the proposed learner profile is a good representation of the learner's preferences.

Comparative Analysis of Various Tools to Predict Consumer Behaviour

With the unstable development of the data accessible on the Internet, WWW has turned into the most capable stage to store, recover, and communicate data. The same number of individuals have taken to the Internet for data gathering, examining client conduct from web get to the logs can be useful to make versatile framework, recommender framework, and clever online business applications. We get to log records are the documents that contain data about the connection amongst clients and the sites with the utilization of the Internet. It contains many points of interest as authentication of users, Address related to IP, time of visit, accessing, data transferred, status setting of result, URL and so on. To analyze web log data for prediction of consumer behavior, various free and paid tools is available online. By studying and comparing various analyzer, a website owner can select the best tool for prediction of consumer behavior. This paper gives a neat report between celebrated log analyzer instruments in light of their highlights and execution.