Dmr 2 Kolokvijum Nova Pitanja

The correct answer is "veza koja povezuje dva klastera" because in the context of social network analysis, a "klaster" refers to a group or cluster of nodes that are densely connected within themselves. Therefore, a "veza" or link that connects two clusters would be the correct answer as it represents a connection between two separate groups within the network.

The correct answer is "broj stvarnih veza u mrezi/ukupan broj cvorova u mrezi" because the definition of metrika mreze links per node is the ratio of the number of actual links in the network to the total number of nodes in the network.

The correct answer is "cvorovi grafa predstavljaju entitete izmedju kojih posmatramo veze" (nodes of the graph represent entities between which we observe connections). This answer accurately describes the concept of nodes in a graph representing entities and the connections between them. It aligns with the understanding that graphs are used to model relationships and connections between different entities or elements.

The given correct answer is "zasicenja informacijama" which translates to "information overload" in English. The explanation for this answer is that the abundance of news, blogs, forums, and wiki data that people are surrounded by every day leads to an overwhelming amount of information. This excessive amount of information can make it difficult for individuals to filter and process the relevant and important information, resulting in information overload.

The most commonly used measures for evaluating the performance of an extraction system are precision and recall. Precision measures the accuracy of the system by calculating the ratio of correctly extracted instances to the total number of extracted instances. On the other hand, recall measures the completeness of the system by calculating the ratio of correctly extracted instances to the total number of relevant instances. These two measures are often used together to provide a comprehensive evaluation of the system's performance.

The correct answer is "broj cvorova u mrezi" which translates to "number of nodes in the network" in English. This means that the size of the network refers to the number of nodes or vertices present in the network. The number of nodes is an important factor in determining the complexity and scale of the network.

Kolaborativno filtriranje koristi podatke sa profila korisnika, parametre konteksta i podatke o ostalim korisnicima. This means that collaborative filtering takes into account the user's profile data, contextual parameters, and information about other users. By analyzing these data, collaborative filtering algorithms can make personalized recommendations based on the preferences and behaviors of similar users.

The correct answer suggests that having trust in a person implies having trust in the topic they are discussing, as well as trust in the person as a whole. This means that trust in both the person and the topic are interconnected and go hand in hand.

The correct answer is "da preporuci sadrzaj iz long tail-a" which means "to recommend content from the long tail". This suggests that the quality of a recommendation system is measured by its ability to recommend niche or less popular content to users. This is important because it shows that the system is not only focused on popular or mainstream content, but also considers the individual preferences and interests of users. By recommending content from the long tail, the system can provide a more diverse and personalized user experience.

Poverenje se različito ocenjuje od strane različitih ljudi, što znači da je poverenje kao pojava subjektivno. Ocenjivanje poverenja zavisi od individualnih percepcija, iskustava, uverenja i vrednosti svakog pojedinca. Ono što jedna osoba smatra kao poverenje, druga osoba može smatrati nepoverenjem. Dakle, poverenje je relativno i zavisi od subjektivnih stavova i mišljenja svakog pojedinca.

When a larger number of recommendations about trust in another party are received, they are combined to form one trust, which means that trust as a phenomenon is composite.

The correct answer suggests that extraction of information and information retrieval are similar processes, but with different focuses. Information extraction involves analyzing texts and presenting only segments of the text, while information retrieval involves finding relevant texts.

The correct answer suggests that real (online) social networks are characterized by the existence of a large number of small, well-connected groups. This means that within these networks, there are many small clusters or communities of individuals who are closely connected to each other. This can be seen as a reflection of how real-life social networks tend to form, with people naturally gravitating towards forming smaller, tight-knit groups within a larger network.

The correct answer suggests that the cold start problem occurs when there is a lack of information about new users or items. This means that there is not enough data available to establish similarity or make recommendations for new users or items. Without this information, it becomes challenging to provide personalized recommendations or match users with relevant content or products.

Transitivity, along with homophily, leads to the formation of cliques. Transitivity refers to the tendency of individuals to form connections with others who are already connected to their existing connections. Homophily refers to the tendency of individuals to form connections with others who are similar to them in some way. When these two factors combine, it results in the formation of cliques or groups of individuals who are interconnected. Therefore, the correct answer is "stvaranje klikova" which translates to "formation of cliques".

The closer the value of the Pearson's coefficient is to 1, it means that the users/items are more similar.

The correct answer is to recommend to the user what suits their needs. This means that the recommendations should be based on the user's specific requirements or preferences, ensuring that the suggested content or products are relevant and useful to them.

The given correct answer is "preferential attachment". Preferential attachment refers to the phenomenon in which new nodes in a network tend to connect more frequently to nodes that already have a high degree or connectivity. This leads to the rich-get-richer effect, where well-connected nodes become even more connected over time, resulting in a highly skewed degree distribution. This process is often observed in various real-world networks, such as social networks and the internet.

If a node is removed from the trust network graph and the edges are redirected to its trusted nodes, and if the connected trust remains unchanged, then it is a trust that has weak overall invariance. This means that even if a node is removed and the edges are redirected, the overall trust in the network remains relatively stable or unaffected.

The correct answer "staromodni pristup dobijanja podataka sa web sajtova" suggests that screen scraping refers to the outdated method of obtaining data from websites. This approach involves extracting information from the HTML structure of a webpage, which can be time-consuming and prone to errors. It is considered old-fashioned because there are now more efficient and reliable methods, such as using APIs or web services, to access and retrieve data from websites.

If adding a trust path in the trust network graph from one node to another does not change the trust between those two nodes, then it is referred to as "poverenje koje ima jaku opstu invarijantnost" which translates to "trust that has strong overall invariance". This means that the trust remains constant regardless of the additional trust path, indicating a high level of stability and consistency in the trust relationship between the nodes.

Roy Thomas Fielding is an American scientist and IT expert who first described HTTP (Hypertext Transfer Protocol). HTTP is the protocol used for communication between web browsers and servers. It allows for the retrieval of resources such as HTML documents, images, and videos from the server to be displayed on the browser. Fielding's description of HTTP laid the foundation for the modern web and has since become the standard for web communication.

The correct answer is "analizira tekstove i prezentuje samo segmente informacija (izvucene iz teksta) za koje korisnik moze biti zainteresovan." This answer suggests that the system analyzes texts and presents only the relevant segments of information extracted from the text to the user, based on their potential interest.

In semantic indexing, the unique naming of entities is achieved through the use of knowledge bases. These knowledge bases contain structured information about various entities and their relationships, allowing for effective indexing and retrieval of relevant information. By utilizing knowledge bases, semantic indexing enables accurate and efficient identification and categorization of entities, enhancing the overall organization and retrieval of information.

The correct answer suggests that "blizina cvorova" (closeness centrality) refers to the proximity of the observed node to the central position. This means that the closeness centrality measures how close a node is to all other nodes in the network, indicating its centrality or importance in the network. The closer a node is to other nodes, the higher its closeness centrality value.

Freebase is a prime example of a knowledge base used for semantic indexing. It was a collaborative knowledge graph that allowed users to contribute and access structured data on various topics. Freebase was acquired by Google in 2010 and became a crucial part of their Knowledge Graph. It provided a vast amount of information that could be used for semantic indexing, allowing for more accurate and relevant search results.

The correct answer is "odredjivanje vrste entiteta" (determining the type of entity). In the context of information extraction, named entity recognition involves identifying and classifying named entities in text. This process includes determining the type or category to which an entity belongs, such as person, organization, location, date, etc. Therefore, "odredjivanje vrste entiteta" accurately describes one of the key steps in named entity recognition.

The correct answer is "profilakorisnika i parametra konteksta" because personalized recommendations are based on the user's profile and contextual parameters. This means that the recommendations are tailored to the individual user's preferences and the specific context in which they are using the recommendation system. By considering the user's profile and the context in which they are making the recommendation, the system can provide more relevant and targeted suggestions.

Housing Maps is one of the first examples of a mashup. A mashup is a website or application that combines data or functionalities from multiple sources to create a new service or feature. Housing Maps specifically combines data from Craigslist, a popular online classifieds platform, and Google Maps, allowing users to search for housing listings visually on a map. This innovative combination of data sources and visualization made Housing Maps one of the early pioneers in the mashup space.

The given correct answer suggests that the method being used is based on the nearest neighbors. This means that the system is using a technique that identifies the closest neighbors or similar users who have purchased product X and also bought product Y. This method is commonly used in recommendation systems to suggest relevant items based on the preferences of similar users.

The correct answer is "jednoznaco ukazuju na ukus/misljenje/stav korisnika" which means "unambiguously indicate the taste/opinion/attitude of users". This suggests that explicit ratings clearly show the preferences and opinions of users, allowing others to understand their perspective.

The correct answer is "veliki deo korisnika na interenetu za koji mali deo korisnika pokaze interesovanje na internetu". This answer suggests that the long tail represents a large portion of users on the internet who show interest in a small portion of information. This aligns with the concept of the long tail, which refers to the phenomenon where a large number of niche products or services can collectively make up a significant market share, even though individually they may not attract mainstream attention.

The given answer states that the similarity between "identifikacija kljucnih tema/koncepata" and "semanticko indeksiranje" is that in both cases, the themes/concepts are not tied to individual words. This means that both processes do not rely on specific words to identify and index the themes/concepts.

In real networks, the connectivity of each member of the network to other members follows a Power Law distribution. This means that there are a few highly connected nodes (hubs) and many nodes with few connections. This distribution is often observed in various real-world networks such as social networks, the internet, and biological networks. It implies that a small number of nodes play a crucial role in the overall connectivity and functioning of the network, while most nodes have limited connections.

The sparsity problem refers to the lack of ratings or evaluations for a particular product or content. It occurs when there are no direct ratings available for a specific item, or when there is a lack of information about new users or items. As a result, it becomes difficult to determine the similarity between users or items, leading to a shortage of user-item pairs for analysis.

The correct answer is "odredjivanje relacija izmedju entiteta" because resolving coreferences in information extraction involves determining the relationships between entities.

Enterprise mashup is an application that combines data from multiple internal and external sources of a company. It typically integrates data from various sources to provide a comprehensive and unified view for users within the organization. This allows for better understanding and analysis of the data, leading to improved decision-making and collaboration among users.

AJAX is a popular method that involves multiple technologies to provide asynchronous loading and displaying of data. It is not a traditional approach for obtaining data from websites and it is not specifically used for detecting SOAP services or a type of mashup architecture. Instead, AJAX allows for dynamic and seamless data retrieval and presentation on web pages, enhancing the user experience by avoiding page reloads.

The correct answer is "oderdjivanje tipicnog prideva entiteta" which translates to "determining the typical adjective of the entity." This suggests that the task involves identifying or determining the characteristic adjective that describes the entity.

The correct answer suggests that noise or interference in the communication process is related only to perceptual barriers that can occur during message reception. It implies that the noise refers to any factors that may hinder the understanding or reception of the message, such as distractions, biases, or misinterpretations that occur in the receiver's mind. It does not include physical factors or external influences that may disrupt the transmission or understanding of the message.

REST (Representational State Transfer) is an architectural style that is used in systems that follow a resource-oriented paradigm. It utilizes the web as an application infrastructure between service providers and service users. This means that REST focuses on resources and their representations, allowing clients to access and manipulate these resources through standard web protocols such as HTTP. It does not rely on session state or complex interactions, making it a scalable and lightweight approach for building web services. Additionally, REST supports various web feed formats for publishing frequently changing information.

The given answer suggests that the image represents a standard for trust. This means that the image is likely showing a representation or explanation of a set of guidelines or criteria that can be used to determine trustworthiness. It could be a standard or framework that helps in evaluating trust levels in various contexts or situations. However, without more context or information from the question, it is difficult to provide a more specific explanation.

The correct answer suggests that the interpretation of degree centrality in the context of social networks is the likelihood that a given person is a mediator between two other individuals in the network. Degree centrality measures the number of direct connections a person has, and being a mediator implies that the person can facilitate communication or interaction between others. This interpretation focuses on the potential influence and bridging role of the individual in the network.