901 Matching Annotations
  1. Nov 2020
    1. But a multi-dimensional poverty assessment, combining various traditional social indicators from GDP per capita to illiteracy rate and sex ratio and indirect data based on advanced technology such as average light index and call detail records, may develop a dynamic data set with geospatial data which can accurately detect the changing phases of the poverty alleviation process and map the poverty level.

      A thorough and coherent critical analysis of the literature that captures many of the salient and important topics that are related to your investigation. You have also done a good job to identify datasets and methods.

    2. They not only increase the delivery cost of various assistance measures and lead to low efficiency of assistance; and in addition, the changes of situation of macroeconomics at home and abroad caused by the epidemic, such as the pressure of maintaining economic growth and the increase of international environmental adverse factors, will also bring more uncertainty to the implementation of various assistance measures, especially some of the hidden problems which are difficult to predict at present may not be revealed until the end of the year, and the overall difficulty of completing the task of poverty alleviation on time will be increased.

      Very interesting description of the poverty related development issues that China is currently facing, especially given recent events (COVID etc...). I do think some of your sentences are too long.

    3. The country has seen a steady decline in the number of impoverished rural residents from nearly 100 million in late 2012 to 16 million by the end of 2018, as shown in data from China’s National Bureau of Statistics. It should reach zero by the end of 2020. (China on its way to end poverty by 2020, 2020)

      interesting introduction, but this paragraph is much too long

    4. Among all the 17 sustainable development goals of the United Nations until 2030, “End poverty in all its forms everywhere” is the first on the list (Tollefson, 2015)

      nice start

    1. These advances are all the more important as society continues to change at a rapid rate and the world’s population continues to climb, especially in developing countries where development issues are the most severe.

      This is an exceptional literature review. Thorough, comprehensive, indicative of your investigative process, coherent, fluid, and generally all round just good work. You identified and critically analyzed a number of salient and topical themes that are related to your research. You also successfully introduced and described relevant data and methods. I will be very interested to see how your methods paper progresses.

    2. It then becomes necessary to devise methods of collecting and measuring the data on these inequalities to be able to better address the complex nature of this issue of gender inequality, both in Nepal and around the world.

      Excellent work identifying themes and topical areas that are related to your investigation

    3. The fact that, within this inequality, women are then subjected to lower levels of care allows one to see that there is a double standard, not only when it comes to the relationship between a husband and his wife or wives, but also in the way that the members of the relationship are valued.

      I also wonder about the cultural beliefs that often perpetuate these types of accepted arrangements

    4. The extremely patriarchal societal structure and high levels of poverty throughout the country combine with traditional views to put women in a place of disadvantage that is more severe than in many other countries throughout the world (Bosco et al., 2019)

      inherency

    5. They not only lack this care, but also the ability to learn how to maximize that care and best raise their children since they often do not complete their education.

      excellent

    6. This often means that the girl drops out of school and remains dependent on her husband, also isolating her from opportunities to participate in the economy, politics, or her community.

      excellent

    7. Women are often expected to remain at home and care for the family and, in many countries, girls are forced into an early marriage because it is believed that marriage and caring for a family is her sole purpose.

      wow, I like it -- straight to the point

    1. More research needs to be done to quantify how much food security is being strained as a result of rapid urbanization in Sub Saharan Africa.

      This is a thorough and authentic investigation into your selected topic. Your sources appear to present local knowledge about the problem, while also providing insight into current data science practices as they relate to urbanization in West and East Africa. You have also done a very good job at identifying themes and topics, in particular the section on the relationship between agricultural lands and urban sprawl was very effective. You were also effective at describing the data and methods used in order to describe and analyze the problem. I wonder if there are any new machine learning methods out there that might be more effective? Overall great work!

    2. Kiambu also has different burgeoning economic opportunities than the other research areas and the region will continue to evolve based on its unique circumstances.

      it's also not far from Nairobi

    3. but none of the aforementioned sources were able to identify the rate of food production in relation to the loss of agricultural land

      good, perhaps this is due to globalization?

    4. Kiio and Achola find this especially troubling for Kenya as a whole as Kiambu County represents a considerable chunk of the meager 17% of fertile land in Kenya suitable rainfall for rain fed agriculture.

      excellent comparison of urban sprawl in Ghana, Nigeria and Kenya

    5. The article cites the country’s history of Apartheid, which prompted people from rural fringes as well as surrounding countries to seek urbanized areas as they fostered a stable economy and better living conditions.

      Very nice use of sub-title to identify topical area. I also particularly like your use of sources that appear to be more local in nature

    6. Researchers use land use land cover maps to quantify the change in land use over various timeframes.

      nice concise introduction to your literature review

    1. Complexity is at the very root of human development. Each region, issue, and system is unique in its way. Whether that be through policies, the economy, or social levels, no one problem is the same. Data science allows us to look at those specific details and provide a solution for that area.

      This is a thorough, detailed and thoughtfully constructed analysis of the literature. You have sucessfully captured the essence of your human development topic while identifying a number of relevant, state of the art methods as they pertain to natural disasters and how to best prepare and respond. I will be very interested to learn which methods you select in the next step.

    2. Another method that was looked at utilized Integrating process-based modeling and Bayesian networks. A lot of the time, when forecasting a storm, scientists will employ a “process-based modeling approach.” This approach takes account of “spatial gradients both alongshore and cross-shore.”

      reads similar to the previous analysis -- would benefit from further editing

    3. This entailed removing subscribers who were not active before and after the cyclone while excluding those destroyed due to the cyclone or belonged to relief workers.

      detailed and thorough analysis, very good

    4. But then the Forecasters’ Dilemma comes into play. This considers the “trade-off” between finding and analyzing data and the need for timely and accurate predictions.

      interesting

    5. Climate action is not only needed, but a detailed and efficient response to its effects is needed as well.

      Excellent description of harm, significance and also the inherent nature of the problem. Section would have benefitted from the use of a sub-title.

    6. It allowed humanitarian agencies to identify where support was needed and which regions were not recovering as well as they had intended.

      adding sub-titles to designate sections would be helpful

    1. By applying an integrated method of human and machine analysis to data collection, the gender-based gap in data collection may finally be bridged, allowing real-world disparities in women’s social, economic, physical, and mental health to be alleviated as well.

      Exceptional critical analysis of the literature on your selected human development topic. Excellent balance in terms of both breadth of topics and depth of focus. I will be interested to learn more about the method you select for in-depth focus. With just an annotated bibliography and a literature review you have covered a remarkable amount of ground through your research.

    2. Dr. Vaitla and his cohorts were also able to produce a machine-learning algorithm that can “accurately identify mental illness” through “genuine self-disclosures” posted on online social platforms with a 96% success rate

      very interesting

    3. One of the clearest, albeit crudest, indicators of gender-based duality in developmental progress is the wage gap.

      section sub-title would be helpful here

    4. Bayesian generalized linear models, artificial neural networks, and repeated cross-validation processes

      perhaps machine learning or deep learning is relevant here?

    5. longstanding patriarchal precepts dominate women’s social interactions, educational opportunities, economic activity, access to healthcare, political engagement, and human security

      excellent

    6. In Amartya Sen’s book Development as Freedom, the famed economist discusses the tenuous balance that often arises between culture and progress on the path towards human flourishing and development.

      very nice introductory sentence

    1. In West’s view, it is not enough to rely on the analytical constituents of big data alone; theoretical frameworks are necessary to understand any kind of collected data.

      a truly important observation

    1. The ability to fully comprehend the complexities and then provide an articulate model makes data science and its techniques unparalleled in its aid in human development.

      This is a remarkably exhaustive, thorough and really in many ways a herculean critical analysis of the literature on your part. Your ability to not only research and identify salient sources as well as to use them within a framework and construct is impressive, especially given the time constraints of the assignment. With more time, I think it would be worthwhile to begin editing the voluminous amount of content you have produced and begin distilling the separate ideas into denser arguments. This simply takes time, and is not possible without first doing exactly what you have done, develop a thorough critical analysis of the literature on your selected topic of investigation. Just good work.

    2. previous approaches to human development have been too narrow in the variables they consider and naive in their analysis of the complexities which followed

      excellent

    3. These findings allow a predictive model which is updated monthly, allowing proper solutions to the ongoing transmission of the Avian Influenza [6].

      useful predictors for training data

    4. logistic regression model that resulted in an odds ratio, where 1 indicated no relationship, greater than 1 is a positive relationship, and less than 1 is a negative relationship

      very good

    5. kernel-based probabilistic classification system which is similar to a bayesian inference

      good, sounds like kernel density estimation or sometimes called PDF

    6. The Use of Geospatial and Remote Sensing Techniques to Track The Increase of Peri-Urban Areas and Associated Health Risks in Disease and Flooding in Vietnam

      Good title - very clear and coherent

    1. For that reason, I propose two central research questions. 1) Within the context of population shifts in the Middle East and Africa, what is the impact of political crises such as terrorism, government instability, or climate change? 2) Can shifts in demography serve as indicators to predict the insurgence of crisis events?

      Overall it's an excellent literature review. I would be interested to know your thoughts on how CDR data, machine learning / neural networks can be used to understand the dynamics of how demographic processes occur over time, rather than more static descriptions of patters that are snapshots. Are there any new machine learning methods that can be joined with CDR data and census data that can begin to give us a real-time high resolution description of human behavior? Regarding your CRQ. How do political sentiments and drastic political events relate to demographics and population descriptions? I will be very interested to know more about your direction in the methods paper.

    2. The synthesis of census data, mobile phone CDRs, and predictive population models reveals a promising future for communicable disease eradication.

      excellent

    3. Gravity-type spatial interaction models have applications in the past and future—they can explain migratory patterns and predict future within-country migration to a staggering accuracy.

      very interesting that you are transitioning from IPF to this -- you're ability to track research on this topic is very impressive

    1. Overall, the sheer scale of data science is what makes it such a powerful tool in human development, and all of its complex implications.

      You have traversed quite a lot of ground over the course of this semester and have settled at the intersection of the very important topic, the use of CDR data to better understand human movement. Excellent work, I look forward to reading more about the methods you are investing. Will you try to go deeper with neural networks and their application within the context of CDR and infectious diseases?

    2. Besides being able to view real-time population mobility, CDR data can be used to predict future mobility patterns. An impedance model implements CDR data to predict how people will move during an epidemic. According to a study where it was used to estimate population mobility during the 2010 Cholera epidemic in Haiti, it can relatively accurately predict the population mobility in the absence of parameters, using only CDR data (Sallah). This makes an impedance model a powerful tool in low-income countries such as those in sub-Saharan Africa. Also, it was especially accurate when predicting the movement of heterogeneous populations, which are prevalent in many low-income countries where people in the same area may have very different levels of wealth.

      this is excellent -- it will be interesting to know if you investigate this method further

    3. Models such as these are inexpensive since they use widely available resources and require little labor. As a result, Low-income countries, such as many Sub-Saharan countries, can take advantage of these neural networks.

      excellent, again I think your paper would benefit from the use of subtitles

    4. Newer methods that implement big data and deep learning algorithms such as Deep Neural Networks (DNN) and Long-Short Term Memory (LSTM) models are more effective (Chae)

      excellent

    5. It will also identify some subsets of people who may be more vulnerable than others.

      Excellent introduction with lots of facts to begin supporting your analysis of the literature. I recommend using subtitles, for example "Introduction" for this section.

    1. Scientists, decision-makers, and ordinary global citizens need access to nuanced, robust information in order to uncover inequities and suffering and, ultimately grapple to find a solution. Data science is the first step.

      It is a very thorough, thoughtful, coherent and fluid literature review. It would have benefitted from further organization by section (subtitles) as well as to further edit paragraphs for length. You have clearly generated a remarkable amount of information on your selected topic and have conducted a productive critical analysis of the literature itself.

    2. Essentially, drastic changes in the climate can strip farmers in Sub Saharan Africa of their livelihoods and they are left with no means to supplement their diets with imported food. Farmers and their families are already suffering.

      Lot's of excellent information in this section, but the paragraph is much too long. Could you have split this up into three or so paragraphs and added an additional subtitle?

    3. Nonetheless, there is a potential relationship between climate change and education, as one investigates the interplay between three development goals: climate action, zero hunger, and quality education.

      Nice introduction -- although I think you could have split this up into two paragraphs. Also, using sub-titles can helpful (i.e. Introduction)

  2. Oct 2020
    1. The scientific question which the author is seeking to answer was finding out which type of land was the most susceptible to climate change in Northern Ethiopia, and the result was those living in lowlands areas.

      Quite excellent -- this is a solid annotated bibliography that clearly defines your research area and provides a good foundation for your continued investigation into the material. You have selected a number of sources that all support your research focus. Questions of water quality and food security are clearly of tantamount important to human development, and your area of focus, Ethiopia and East Africa, is a location ripe for study. You did a good job identifying data sources and also began to identify some methods. I look forward to your critical analysis and the continued direction of your work.

    2. data from remote sensing of satellite imagery of Northern Ethiopia, as well as previous data, and identifies where the best relative sources of water are

      good

    3. the study showed that there were 341 km^2 of land measured, and showed about 43% of land usable, about 40% of land somewhat usable, and about 18% of land unusable for irrigation

      excellent

    4. The article and study were successful at finding the areas in Ethiopia where access to clean water was needed the most, which was the question that was trying to be answered.

      this article clearly contributes to your research focus

    5. The study examined in this article was conducted in 2016, and was able to receive data from over 10,000 homes. This survey used a structured questionnaire, and from the results, statistical analysis was able to be applied.

      good

    1. By using Big Data, businesses were able to provide more timely and effective aid to those affected by the earthquake, Through monetary and service aid, data in humanitarian efforts help accelerate disaster response and management.

      Excellent work. Very clear definition of your intended research direction. You have identified a number of sources that describe the landscape of the literature as it pertains to disaster response. You have also done an effective job of identifying sources and types of data that will be important to your investigation. Continue to think about how the data is being used in the context of different methods. How is the CDR data being used? Did the authors talk about the radius of gyration? How about gravity or impedance models? These types of methods may be interesting for you to pursue further as you transition from your critical analysis towards a methodology.

    2. However, in places that are more rural and have smaller populations, there are fewer cell phone towers. Since disasters can damage the towers, this method would prove utterly useless. Furthermore, the researches explain that in more rural regions, mobile phone usage is lower among “children, the elderly, the poorest, and women.” This can lead to a bias in the data, which is something the researchers are trying to avoid inc comparison to earlier methods.

      excellent -- gets to the inherent nature of the problem

    1. By applying an integrated method of human and machine analysis to data collection, the gender-based gap in data collection may finally be bridged, allowing real-world disparities in women’s social, economic, physical, and mental health to be alleviated as well.

      Excellent annotations. A very good cross-section of sources related to the focus of your investigation. You have done a good job balancing themes and topics while also beginning to introduce some methods. You have also been successful in describing some of the issues that are inherent obstacles towards more accurately describing gender inequities (via data collection). I will be interested to know more about the data and methods being used to describe, analyze and predict gender inequality at large scale.

    2. By layering a series of localized partial perspectives over geospatial data collected using an approach of positivist epistemology, however, Bosak and Schroeder argue that a “more objective representation of reality” can emerge (235), allowing for a more accurate vision of development within the context of southeast Asian cultural norms.

      interesting

    3. chart literacy, stunting, contraception use, and income rates on various geographic scales with a relatively small margin of error “in the range of 2-30% explained variance…

      good

    4. geospatial covariates with correlating, pre-established data pools to more accurately predict social, health, and economic phenomena in both tiny pockets and large swathes of land

      good

    5. As implied by Amartya Sen in his book Development as Freedom, both the social and economic aspects of development mentioned in this article must be monitored carefully in order to dismantle the unfreedoms that prevent women from achieving them.

      good general annotation that is site specific and provides valuable contextual information on your topic

    1. Vietnam serves as an interesting and important case study to not only attempt to alleviate the ailments of the area, but also to serve as a groundwork for similar areas in the future.

      Excellent work. Thorough and comprehensive. I have a clear understanding of your research direction as well as some of the topics that will be of interest to your work. You have touched on a number of different salient themes and topics while also identifying harms, significance and some of the inherency associated with these problems. You did a good job beginning to identify datasets. Keep moving forward with the methods, you began to introduce some good ones in the last annotation. Just keep going!

    2. The 9 classifications it was able to identify were water, urban and built up, rice, other crops, grasslands, orchards, barren, forest, and mangrove

      excellent

    3. However, the increased amount of housing meant that groundwater was being extracted and pushed down to lower elevations, causing a dramatic increase in flooding for those houses which were built at a lower elevation.

      inherency

    4. whether there was a correlation between the increased urbanization of Beijing and nitrogen dioxide levels in the troposphere. They found a strong correlation between both variables using a scatter plot where the correlation coefficient was .9036 and the coefficient of determination was .821. This illustrates a positive correlation between the two variables.

      excellent

    1. When developing countries no longer have to focus on life threatening diseases such as malaria, freedoms in other areas such as social and economic opportunity will promote development in all other aspects of life.

      Excellent annotations. Thorough, thoughtful, and comprehensive. You have done a very good job at identifying many of the important themes and topics associated with development as they intersect with two or three different subject areas. I would like to know more about the data and also about some of the methods used to describe, analyze and predict future outcomes. I will be very interested to learn more about the critical analysis you produce and the path you select moving forward.

    2. Such residential and commercial building projects have led to a significant decrease in agricultural land, a concerning trend considering the county’s rapid rise in population

      This is common in many places globally, as fertile agricultural lands are often in close proximity to some of the largest cities (in this case globally) and they are often targeted for development due to the east of profit from land use transition (agriculture to low density single family housing). This is one of the major drivers of urban sprawl

    3. unplanned urban development often leads to major flooding, air pollution, deforestation, soil erosion, and desertification

      good identification of potential problems resulting from poor planning and land development

    4. urban planning and management, slum upgrading, crime reduction, transport and traffic management, and waste management

      all excellent areas for further investigation

    5. Nearest Neighborhood Analysis and Weighted Sum Analysis was also used to compile various sources of data to assess PHC accessibility for the native population

      good

    6. there are myriad factors that go into determining which areas have access to adequate healthcare facilities. Such factors include availability of quality roads, travel distance, travel speed, mode of transport, PHC population coverage, and topographic impediments such as bodies of water, forests, or rugged terrain

      good

    1. As stated above, accurate population data is imperative for effective management of public health and effective healthcare, which is probably the aspect of human development I will be focusing on.

      Excellent annotations. I particular like how you progressively developed your focus on machine learning methods, while still coupling human development research oriented questions. I'm wondering, did you find any recent research that focused on using neural networks?

    2. Finally, the model assumes that no one lives in unsettled areas, which is likely false.

      This is a difficult area to accurately describe. On the one hand, adding "noise" to the model may introduce too many persons/households in the rural areas, while trying to account for the zero-cell problem by reallocating to urban densities may also miss the mark. We need a better method to estimate rural household densities and locations. I suspect may be an area that is ripe for further investigation.

    3. To create the models of Beijing’s urban development over time, radar backscatter data collected from QSCAT satellites and modified using a DSM (Density sampling mean) method to format it into a grid. The DSM method was used to overcome the weakness of QSCAT data, which is its low spatial resolution.

      interesting

    4. Population tracking is imperative to understanding the spread of a virus, and how to mitigate it, so these methods are incredibly useful in the domain of public health.

      good

    5. Using GPS data from social media, such as twitter geotags and location data from web browsers, is more accurate then CDR data.

      also, is it readily available?

    6. Models that have used CDR data, such as ones used to try and eliminate malaria in sub-Saharan Africa, have been successful in identifying transmission routes and local foci.

      CDR is definitely effective for modeling transport activities and the associated spread of disease (infectious / vector borne). Check our the impedance model, gravity models, radius of gyration methods and other similar approaches.

    7. The maternal mortality rate in sub-Saharan Africa is high in comparison to the rest of the world, at 546 deaths per 100,000 live births, and this number has declined at half the rate of the rest of the world. The key factor relating to this problem has shown itself to be skilled birth attendance during childbirth.

      Good, harms, significance and inherency all in the first two sentences.

    1. further inquiry

      This is an exceptional annotated bibliography that is packed with annotations, analysis and added value squarely at the intersection of human development and data science. I encourage you to keep moving forward with your investigation in the direction of some of the more sophisticated approaches. DHS data with hierarchical bayesian models, use of CDR data and other similar types of methods are well worth your time to investigate further in order to more fully describe gender equality (or inequality) as a (complex and adapting) development process. Superb work!

    2. STATA

      STATA is a little bit old -- although some researchers still like to use it. Implementations with python or R are likely more state of the art and typically associated with machine learning methods.

    3. it proves that changes to the gathering methods must be made so that the specific issues caused by gender inequality can be addressed, not just issues plaguing the general population

      do you think this also begins to introduce questions about rights to privacy?

    1. Identifying older disabled people might inspire a push to prioritize their freedom to participate in the market as they have outgrown their public school ages, and are therefore excluded from the annual census.

      A strong collection of sources that have been thoroughly annotated. You have clearly defined your area of investigation and stakes out its landscape with a few sources. I will be interested to see where you go with the data and data science aspect with regard to this topic. I expect there are a few distinct directions you could take in proceeding. Excellent work!

    2. Rather than posing the freedom to learn as a basic freedom, they emphasize the exclusion of disabled students as an unfreedom

      important to articulate this

    3. As it stands today in the United States, which has one of the most impressive special education programs in the world falling behind European natitons, the schools are often criticized for collapsing the amount of cognitive levels they separate the students into

      reword this sentence, your meaning is unclear

    4. Few emerging nations collect data on children with disabilities and those that can do not know how to effectively integrate disabled students into their exclusive education systems

      significance and inherency, as well as the salient nature of your investigation -- excellent start

    1. Therefore, although the researchers came to an interesting conclusion, it would be beneficial to look at this problem in a more holistic manner.

      Excellent work. You have clearly defined the boundaries of your investigation and staked out a few sources to populate the landscape. You also introduced sources that provided perspective from both a local perspective as well as from a more global viewpoint.

    2. The most challenging part of this facet of food security is that effective climate change mitigation policy may in fact hurt developing countries.

      inherency

    3. The scientists end by entreating people to heed the warning of these IPCC projections and begin to address climate change, in tandem with investing in heat-tolerant plant strain and specialized irrigation systems, especially in underdeveloped areas like the Sahel.

      interesting source that offers a more global perspective on your area of investigation

    4. Taking these researchers’ conclusions into account, it may be possible to achieve both these goals with a single approach.

      good source -- seems to describe results from a typical household survey. Do you think their model can be used to inform new types of data science methods?

  3. Aug 2020
  4. Jul 2020
    1. This method is useful as it simplifies images without letting go of the message of the image.

      I like your use of the term message. Sometime I have also heard this concept referred to as the signal.

  5. caroline-wall.github.io caroline-wall.github.io
    1. this course itself is about teaching machines how to learn like a brain in order to make predictions and analyze data about the world around us. Two, this data we analyze is often about ourselves and our brains: our effect on the environment, the social sciences, etc. Data science

      excellent