--- title: "Web structure/content/usage mining; privacy" subject: "Data Mining" chapter: 7 key: "semester_7/data_mining:web-structure-content-usage-privacy" source: https://www.bctengineer.com/q/semester_7/data_mining/web-structure-content-usage-privacy site: BCT Engineering --- # Web structure/content/usage mining; privacy Data Mining · Chapter 7: Advanced Applications - Asked in: year not given, 5+3 marks; year not given, 6+3 marks - Video: [Data Mining Lecture - - Advance Topic | Web mining | Text mining (Eng-Hindi)](https://www.youtube.com/watch?v=sP_8wK7Ax88) — Well Academy - Answer checked by Claude Opus 5.5 (high effort) on 2026-10-14 - Page: https://www.bctengineer.com/q/semester_7/data_mining/web-structure-content-usage-privacy - Whole chapter: https://www.bctengineer.com/md/semester_7/data_mining/chapter-7 ## Question Explain Web Structure/Content/Usage mining. Explain the privacy aspects of Data Mining. ## Short answer Web content mining extracts knowledge from page contents; structure mining analyses hyperlinks using PageRank and HITS; usage mining discovers user patterns from logs. Privacy issues include collection without consent, inference, profiling and re-identification. Remedies include anonymisation, perturbation, differential privacy, consent policies and legal protection. ## Answer #### Web content mining It extracts useful knowledge from the **contents of web pages**: text, images, audio, video and structured tables. It uses text mining, classification and clustering of documents, information extraction, summarisation and opinion mining. *Example*: classifying news pages into sports, politics, and so on; extracting product prices from shopping sites. #### Web structure mining It studies the **hyperlink structure** of the web, a graph with pages as nodes and links as edges, to find which pages are important and how pages are related. - **PageRank**: a page is important if important pages link to it. - **HITS**: finds *hubs* (pages linking to many good pages) and *authorities* (pages linked from many hubs). - Also community discovery, and focused crawling. *Used in* search engine ranking. #### Web usage mining It discovers user access patterns from **web server logs, proxy logs, cookies and click-streams**. 1. *Preprocessing*: data cleaning, user identification, session and page-view identification. 2. *Pattern discovery*: association rules, sequential patterns, clustering of users and classification. 3. *Pattern analysis*: filtering and visualisation. *Used for* personalisation, recommendations, improving site design and caching, and fraud detection. ```text Web mining Content -> what is on the page Structure -> how pages are linked Usage -> how users behave ``` #### Privacy aspects of data mining - Personal information is collected and mined **without informed consent** (browsing history, purchases, location). - Combining data from many sources allows **inference of sensitive facts** and re-identification of "anonymous" data. - Profiling can lead to discrimination, and data can be misused or sold. - Web usage mining with cookies and logs tracks individuals across sites. - **Remedies**: privacy-preserving data mining (anonymisation, perturbation, differential privacy), consent and clear privacy policies, data minimisation, access control and encryption, and legal protection (e.g. the Privacy Act, 2075 of Nepal, GDPR). ## Check yourself The answer's key points as multiple-choice questions, with the correct option and why. 1. What is the idea of PageRank? A. A page is important if important pages link to it B. A page is important if it has many words C. A page is important if it was visited by many IPs D. A page is important if it is newest Answer: A. PageRank is based on links from important pages. (Key point: PageRank) 2. In HITS, what is a hub? A. A page linked from many hubs B. A page that links to many good pages C. A page with the most text D. A server log file Answer: B. Hubs link to many good pages; authorities are linked from many hubs. (Key point: HITS) 3. What are the usage mining steps in order? A. Pattern discovery, preprocessing, analysis B. Pattern analysis, discovery, preprocessing C. Preprocessing, pattern discovery, pattern analysis D. Preprocessing, analysis, discovery Answer: C. Data is first cleaned and sessionised, then patterns are discovered, then analysed. (Key point: Usage mining steps) 4. Which is a privacy risk specific to web usage mining? A. Cookies and logs can track individuals across sites B. Hyperlinks are removed C. PageRank becomes zero D. Pages become unstructured Answer: A. Cookies and logs allow tracking of individuals. (Key point: Privacy) ## Related in Data Mining - [CRM; security and privacy of data mining](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Acrm-security-privacy) — Data Mining, chapter 7 - [Web mining structure and challenges](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Aweb-mining-structure-challenges) — Data Mining, chapter 7 - [Web mining, importance and techniques](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Aweb-mining-importance-techniques) — Data Mining, chapter 7 - [Web log mining and WWW mining architecture](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Aweb-log-mining-architecture) — Data Mining, chapter 7 - [Short note: Security and privacy in DM](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Asecurity-privacy-note) — Data Mining, chapter 7 - [Data mining and its applications](https://www.bctengineer.com/question.md?key=semester_7%2Fdata_mining%3Adm-banking-biomedical) — Data Mining, chapter 1 ## Related in other subjects - [Text mining vs web usage mining](https://www.bctengineer.com/question.md?key=semester_8%2Finformation_system%3Atext-mining-vs-web-usage-mining) — Information System, chapter 7 - [Web mining with structure mining](https://www.bctengineer.com/question.md?key=semester_8%2Finformation_system%3Aweb-mining-structure-mining) — Information System, chapter 7 - [Main aspects of the Semantic Web](https://www.bctengineer.com/question.md?key=semester_7%2Fweb_technology%3Asemantic-web-aspects) — Web Technology, chapter 9 - [Web mining importance and types](https://www.bctengineer.com/question.md?key=semester_8%2Finformation_system%3Aweb-mining-importance-types) — Information System, chapter 7, asked 3×