Computational Social Science Methods Coursera Quiz Answers 2022 | All Weeks Assessment Answers [💯Correct Answer]

Hello Peers, Today we are going to share all week’s assessment and quiz answers of the Computational Social Science Methods course launched by Coursera totally free of cost✅✅✅. This is a certification course for every interested student.

In case you didn’t find this course for free, then you can apply for financial ads to get this course for totally free.

Check out this article – “How to Apply for Financial Ads?”

About The Coursera

Coursera, India’s biggest learning platform launched millions of free courses for students daily. These courses are from various recognized universities, where industry experts and professors teach in a very well manner and in a more understandable way.

---

Here, you will find Computational Social Science Methods Exam Answers in Bold Color which are given below.

These answers are updated recently and are 100% correct✅ answers of all week, assessment, and final exam answers of Computational Social Science Methods from Coursera Free Certification Course.

Use “Ctrl+F” To Find Any Questions Answer. & For Mobile User, You Just Need To Click On Three dots In Your Browser & You Will Get A “Find” Option There. Use These Option to Get Any Random Questions Answer.

About Computational Social Science Methods Course

This course provides an overview of current opportunities and the pervasiveness of computational social science. Every day, we see the results, ranging from the services provided by the world’s most valuable companies to the hidden influence of governmental agencies and the power of social and political movements.

Course Apply Link – Computational Social Science Methods

Computational Social Science Methods Quiz Answers

Week 01: Computational Social Science Methods Coursera Quiz Answers

Module 1 Quiz Answers

Q.1 Social science has always been very complex, so why is computational social science just right now becoming as relevant as it is?

• The digital revolution just recently provided the data and the computational power
• The problems society faced in the past were not as urgent
• There was not a critical mass of social scientists with enough math training
• The problems society faced in the past were not as pressing

Q.2 The amount of information that can be stored in the world grows very fast. How much more new information can the world store every two to three years?

• The same as it was able to store since pre-history
• About the same amount stored by the U.S. Library of Congress
• The equivalent of a pile of books that reaching from Earth to the Sun
• About the same stored by the historical Library of Alexandria

Q.3 Comparing the amount of information that can be store by the world’s technological devices, with the amount being stored by all human DNA, what have we seen?

• Technological capacity is still minuscule comapred to the amount of DNA code
• Technological storage can already store more than all human DNA
• Human DNA can still store more, but will be overtaken in the foreseeable future
• Technology can store about as much information as it stored by the DNA of one single human being

Q.4 On basis of what argument was it claimed in the lectures that the Social Sciences are the most complex of all sciences?

• Because humans are unique in that they have something akin to intelligence
• It is based on and subsumes the dynamics of physics, chemistry, and biology
• It has to account for 7.5 billion individuals, more entities than other sciences
• Because when people are put in different situations, they behave differently

Q.5 Reviewing the historical context of science, we learned about so-called problems of ‘simplicity’, ‘averages’, and ‘organized complexity’. Which of the following statements is true?

• Problems of simplicity are modeled with a small number of interacting variables
• Problems of averages are modeled with a sizable number of organically interrelated variables
• Problems of complexity are modeled with known distributions that summarize many variables
• Problems of averages are modeled with a small number of interacting variables

Q.6 With computational technology, social science studies have recently started to make predictions with accuracy up to:

• 80-90%
• 40-50%
• 100%
• 10-20%

Q.7 According to the eminent political scientist Jean-J. Rousseau, there is an important emergent phenomenon we have to consider when dealing with democratic will formation. What is it?

• That it is possible to predict suicide rates, even so this is a free will decision
• The invisible hand is the collective current containing only a spark of the free will
• Fake news is particularly worrisome in the age of social media bots
• What we want can be different from what I want plus what you want

Q.8 In the book Godel, Escher and Bach, an anteater interacts with a socially emergent entity. What is it?

• An ant colony
• The environment, consisting of the forest and rivers
• An individual ant that understands the whole
• The cast of worker ants

Q.9 The scientific method based on making observations by collecting data is called:

• Theoretical method
• Dynamical method
• Empirical method
• Analytical method

Week 02: Computational Social Science Methods Coursera Quiz Answers

Web Scraping Assigned Task

Q.1 For this assignment, you will web scrape videos from two YouTube channels. This quiz is designed to assign different learners two channels at random, so you might see slight variances than your peers.

• You will scrape both featured & recommended videos from TED-Ed and SciShow.
• TED-Ed is a YouTube channel from Ted which creates short animated educational videos aimed at children. It also has its own website. TED-Ed lessons are created in collaboration with educators and animators. It has over 8.5 million subscribers and over 1.25 billion views as of February 2019. Sci Show is a YouTube Channel where “Internet Guy” Hank Green delves into the science behind current events with a skeptical eye and a dash of humor.  SciShow was launched as an original channel. 
• The two channels are quite different in nature, but both are popular education channels. Let us have a look at the videos the audiences of each channel are exposed to. Find the link to the channels below:

Module 2 Quiz

Q,1 What could be wrong with drawing generalized conclusions for society from digital footprint data from Google searches, dating websites, or Twitter feeds?

• The observed people are not necessarily representative of everyone
• Obtaining scraped data is against academic ethics
• You might discover uncomfortable facts about race and marriages
• Digital footprints are always purposefully manipulated by companies

Q,2 In lecture, we used the analogy that “digital footprint is to the social sciences, what the telescope was to physics”. What did this refer to in the context of social science?

• The digital footprint is very expensive to obtain, like previous data collection technology
• Digital traces are collected through sophisticated and omnipresent sensor technology
• Just like a telescope, you have to turn on data collection to obtain the digital footprint
• It finally allows us to convert ideas and natural observations into scientific observations

Q,3 Which of the following is in line with Professor Blumenstock’s work in using new data and new methods to understand causes and consequences of poverty?

• Using online surveys to make census work cheaper and more complete
• Using credit card transaction data on purchases
• Using online experiments to predict rural connectivity
• Using mobile phone trace data to predict poverty

Q,4 Since a census is the traditional procedure of systematically acquiring information about all members of a given population, it is crucial to understand the people that make societies. It comes with many challenges. What is NOT one of them?

• They are expensive and difficult to implement
• They violate citizens’ basic right of privacy
• They are often outdated, as some countries have not done them for over 20 years
• They are not accurate and necessary

Q.5 In developing countries, the most commonly available sources for digital footprint data are:

• Facebook and Twitter
• Mobile phone and satellites
• Census and household surveys
• Traffic cameras and Google Maps

Q.6 In order to understand the relationship between digital trace data and poverty, Prof. Blumenstock from UC Berkeley used the following data sources in a case study in Rwanda:

• Census data (through official statistics) + social media posts
• Survey responses (by calling people) + mobile phone logs
• Quality of life (through machine learning) + credit card records

Q.7 Why does Prof. Blumenstock from UC Berkeley work with both mobile phone log data and survey responses, collected by calling people?

• People lie in survey responses, especially when researchers call them over the phone
• Mobile phone trace data by itself is not reliable, since people turn their phones off and on
• To make time-series prediction for the next five years and for the time before mobile phones
• Survey data provides the ground truth about poverty used to learn the model from digital trace data

Q.8 Why does Professor Blumenstock finally compare the poverty predictions made on basis of his mobile phone trace data with poverty data from public sources?

• To validate predictions obtained from surveys and mobile phone traces
• To incorporate public data into the training set of his model
• To correct the mistakes in the mobile phone log data provided by the phone operator
• To make time-series prediction for the next five years and for the time before mobile phones

Q.9 data science, as used by Prof. Blumenstock from UC Berkeley, what is “feature engineering”?

• Convert poverty data about people into unrelated digital footprints
• Inventing new data features so it can confirm a given hypothesis
• Convert raw data into a set of ‘features’ that can be input into a model
• Deleting those features from the digital footprint that rejects our hypothesis

Q.10 In contrast to modern machine learning approaches, traditional programming approaches feed what into the computer, in order to produce what in return?

• They are feed data and the output, to produce a program
• They are feed a program and output, to produce a data
• They are feed data and a program, to produce the output

Q.11 Prof. Blumenstock from UC Berkeley used survey data to detect features in mobile phone log data, and then tests the accuracy of the obtained model by comparing it to National Household survey data from the National Institute of Statistics (in this case study, from Rwanda). How high was the obtained accuracy (correlation) of the ‘big data based’ prediction?

• Some of them sporadically matched, but trace data was much more detailed
• Half of them matched, but trace data was much cheaper and quicker
• Fairly high (correlation of 0.92, or over 80 % accuracy)
• Not very high, but as computing power will increase, it’ll improve quickly

Q.12 We have seen several benefits arising when mobile phone log data is used to predict poverty levels. Which one was NOT one of them?

• It is faster, and therefore allows for fast response
• It is more accurate than traditional survey and census collections
• It is cheaper, and therefore allows for more frequent collections
• It is faster and cheaper, and therefore allows new ways of evaluating impact

Q.13 At the end of his lecture, Prof. Blumenstock from UC Berkeley concluded that digital trace data:

• Will inevitably soon replace traditional surveys
• Can be used complementary to traditional data collections
• Are more expensive, but are more detailed than traditional methods
• Should be fostered to take the place of official statistics

Week 03: Computational Social Science Methods Coursera Quiz Answers

Module 3 Quiz

Q.1 The subfield of Artificial Intelligence dedicated to process and analyze large amounts of natural language data is generally known as:

• Social Network Analysis
• Natural Language Processing
• Big data machine learning
• Social Media Trends Analyzer

Q.2 Before we had flying machines, we assumed we would need feathers to fly. How can we relate this idea in aerodynamics to today’s digital world?

• It is very productive to follow the insights from nature to create new technology
• The laws of nature are sometimes wrong
• We don’t necessarily need a brain to build intelligence
• Humans are stupid, and we need conscious machines to create technology

Q.3 After the so-called ‘last battle of human kind against the machine’, when the Chess Grandmaster Garry Kasparov lost to Artificial Intelligence (more than 20 years ago), how did Kasparov himself react to that defeat?

• He promoted the idea to cooperate with machines in chess
• He argued to shut off all machines, immediately
• He went into the mountains, hiding from the Terminators
• He created more chess schools, arguing that humans have to become better in chess

Q.4 Artificial Intelligence has recently become more effective at solving complex problems because: 

• We have developed more powerful regression algorithms to analyze statistical data
• Companies like Facebook and Google have made all of their deep learning neural networks openly available to the public, which unleashed the current AI revolution
• Quantum computers have allowed us process data using qubits that are much faster than how traditional computers
• The big data footprint has made more data available and faster processors are now able to analyze that data

Q.5 Regression analysis is a traditional statistical technique, going back to the early 1800s. Today’s suite of machine learning approaches made it obsolete and irrelevant.

• False
• True

Q.6 What kind of danger would it bring to consider too many parameters, that is, too many characteristics that can help in classifying a particular system or event?

• Overfitting to specific contexts
• Not being able to explain the system
• Non-parametric distributions
• Bias toward certain perameters
• None, since more detail is always better

Q.7 What is a testing set in machine learning?

• A series of tests to see if an algorithm passes the Turing test
• A part of the dataset used to check the accuracy of the algorithm
• A part of the dataset used to identify the decision-making rule
• A set of algorithms used to test artificial intelligence

What is purpose of reserving a validation set that is not used when training a machine learning algorithm?

• To validate complementary patterns in the data, which will then undergo data fusion
• To validate that the algorithm can only be trained with big data
• To validate how good the algorithm is
• To decide which decision rule generalizes best

Week 04: Computational Social Science Methods Coursera Quiz Answers

Module 4 Quiz

Q.1 We have seen examples of the diffusion of innovation and the diffusion of diseases in schools. Two kinds of data have been important to understand what was going on in these cases.

• Who subjects are & with whom they connect in their social networks
• Their mobile phone logs & their level of poverty
• Their moral frames & their neurological connections

Q.2 According to Prof. Fowler’s studies, obesity clusters are:

• Found even beyond the scope of one degree of immediate friend group
• Mostly due to exogenous factors such as genetics and environment
• Always driven by homophily, not by context
• Following a normal distribution from random clustering to distinct patterns

Q,3 Which of the following saying was used to refer to the concept of “homophily”?

• “Hit two birds with one stone”
• “Birds of a feather flock together”
• “Early bird gets the worm”
• “If you’re a bird, I’m a bird”

Q.4 Which factor was NOT one of the main three contributing factors Prof. Fowler identified as causes for clustering of similar people in a social network?

• Influence; like a domino effect
• Homophily; drawn to similar attributes
• Generosity; giving more to friends
• Context; mutual exposure to a same environment

Q.5 Prof. Fowler from UCSD presented empirical studies that showed that people gather in different kinds of social clusters. This included all BUT NOT the following:

• Brain size, smart people connect together in social clusters
• Obesity, overweight people connect together in social clusters
• Drinking, people who drink alcohol connect together
• Happiness, happy and unhappy people connect together

Q.6 What did the researchers find from the generosity experiment from Prof. Fowler at UCSD?

• The big picture of a network wouldn’t change even an individual becomes more generous
• It is limited to influencing only your first-degree friends
• Even just one person being more generous can affect the whole network
• It takes three people being more generous at the same time to start a generosity contagion

Q.7 According to Professor Fowler’s studies, who has more social influence on you in an online network?

• Facebook friends with verified information as your friends in the real world
• Famous celebrities, especially when they are among the top in terms of followers
• People who you follow in both Facebook and Twitter
• Facebook friends who follow each other mutually

Q.8 True or False. Prof. Fowler from UCSD showed ample evidence that social networks lead to the fact that others have large and detectable social influence on you, reaching from obesity, over smoking to having a grumpy face expression. He therefore concludes that people should rely more on themselves, as self-confident individuals.

• False
• True

Q.9 Big data analytics provides a powerful tool for the social sciences, governments, and businesses. It is, however, no panacea. There is an ultimate limitation to the power of big data:

• Data is always from the past and by itself cannot predict future dynamics different from the past
• Producing data is expensive and the skill gap leads to a lack of data analysts
• Most big data sources consist of unstructured and qualitative data and cannot be analyzed

Q.10 Which of the following is true about models?

• Cubist chickens are the right way to model complex systems
• Complex systems like birds in flight are too random to model accurately
• The fine details of a model are not very important
• There is no single best way to model a system

Q.11 Why do we still need models when we can collect and analyze data in real life? (three of the four options are correct)

• Models are driven by AI that is more powerful than statisticians are
• Explore imagined and counterfactual scenarios
• Explore consequences of our assumptions
• Identify questions for empirical research

Q.12 What did we learn from a model of hare and lynx populations?

• Interdependencies can lead to predictable social patterns
• With lots of lynx, the number of hares will increase
• With lots of hares, the number of lynx will decrease
• Their joint fluctuations are mainly due to external environmental factors

Q.13 Axelrod’s cultural model can explain an array of societal macro patterns, including the formation of between-group boundaries, within-group congruity, and cultural isolation. What are the two simple assumptions for the dynamics of the simulated individuals that lead to these macro-behaviors?

• Rich individuals become more educated & different races do not mix
• Neighbors aim to gain resources & older agents loose skills
• Skills are unfairly distributed among agents & agents move toward likeminded ones
• Neighbors interact with similar ones & interactions influence others

Q.14 In lecture, we saw the long-serving Chair of the U.S. Federal Reserve making a confession that, according to him, was the cause for making decisions that contributed to the 2008 recession. What was it?

• His advisors were corrupt
• He had unethical intentions
• His prediction was short-sighted
• His model was inaccurate

Q.15 What is meant when people say that “All models are wrong”?

• Theoretical computer simulations are not calibrated with empirical data
• The digital footprint is not representative, but always biased
• All models are just a simplification of part of reality
• Scientific models are useless, even computational science

More About This Course

This course provides an overview of current opportunities and the pervasiveness of computational social science. Every day, we see the results, ranging from the services provided by the world’s most valuable companies to the hidden influence of governmental agencies and the power of social and political movements. They are all researching human behavior in order to influence it. In short, they all conduct social science through computational means.

This course addresses three questions:

I. Why is Computational Social Science (CSS) being studied now?
II. What is covered by CSS?
III. What are some CSS examples?

This final section provides an overview of four major CSS applications. To begin, Prof. Blumenstock of UC Berkeley discusses how we can gain insights by studying the massive digital footprint left behind by today’s social interactions, particularly in order to foster international development. Second, Prof. Shelton of the University of California, Riverside, introduces us to the world of machine learning, including the fundamental concepts underlying this current driver of much of today’s computational landscape. Prof. Fowler of UC San Diego introduces us to the power of social networks, and Prof. Smaldino of UC Merced explains how computer simulation can help us solve some of the mysteries of social emergence.

WHAT WILL YOU LEARN?

• Examine the history of social science and the current challenges it faces as a result of the digital revolution.
• Set up a machine to create a database that can be analyzed.
• Discuss artificial intelligence (AI) and how to train a machine.
• Learn how social networks and human dynamics create social systems and patterns.

Conclusion

Hopefully, this article will be useful for you to find all the Week, final assessment, and Peer Graded Assessment Answers of the Computational Social Science Methods Quiz of Coursera and grab some premium knowledge with less effort. If this Computational Social Science Methods really helped you in any way then make sure to share it with your friends on social media and let them also know about this amazing training. You can also check out our other course Answers. So, be with us guys we will share a lot more free courses and their exam/quiz solutions also, and follow our Techno-RJ Blog for more updates.