In “‘A Report Has Come Here’: Social Network Analysis in the Papers of Thomas Jefferson“, Klein tells the story of Thomas Jefferson’s relationship with one of his slaves, James Hemmings. The focus on this relationship illustrates how much of the history written about American Slavery is missing perspectives and stories about the relationships between slaves and slaveowners. As CM-A mentioned in their post, most of the information we have from this time is written by white upper-class men so digging deeper into the absent stories can help piece together many more voices. Klein develops an interesting framework about how to deal with these absences in stories by using a social network analysis. It seems to be very difficult to piece together information about relationships during a time where correspondences weren’t digitized, but one can understand the importance (frequency of correspondence) of relationships using social network analysis. I think Klein’s work is a strong step in understanding more about these absent histories but there are still strong limitations on what can be done.

I liked reading the (unnamed?) paper by Warren et al.  The main goal of their project was to digitally create a map of how early modern people were related and interacted.  They describe a number of challenges they face in doing this, such as the lack of documented info from some time periods.  Although I couldn’t fully understand all of their statistical techniques, I understood their methodology for the most part.  One important takeaway was not inferring causation from correlation.  In their example, they show how two people could be mentioned by the same person, but could have no ties to each other.  They also used topic modeling which we have recently been talking about and working with.

nickbeati talked about “margin of error” in their modeling.  They deemed a 7% margin of error from looking at a random 200-entity set and reviewing for accuracy.

I enjoyed reading this because I had never thought of this idea as a research topic.  I imagine doing this project in a hundred years for our time period will be much easier!

We are fortunate with the use of computers, smartphones, and other forms of media the great avenues to which we can explore data. This can sometimes, though, lead us down somewhat of a rabbit hole, in which we can’t really draw any conclusions or question the intent of our research. At first glance reading “A Report Has Come Here”, I was left thinking this after learning a little about computational linguistics. In this technique, data researches are able to manipulate data “that allows you to present textual data in various visual forms.” I’ve included an example from the article below. From there, we are able to draw complicated links between various objects, people, etc. This connects to a reading we did last week involving deep reading. There are a lot of exciting challenges to discover using this method, but I am honestly not a big fan of it. For me at first glance, it was extremely confusing to draw connections between the arrows and I felt utterly confused at the data displayed and more importantly, the intent behind the visualization.

JH makes a good point in his post that these extraction methods are important.  He highlights that, “James Hemings could have easily been forgotten in history, but thanks to various digital techniques, information regarding Hemings could be uncovered.” These various extraction approaches do serve a purpose, but as an economics major, I believe there are more sophisticated ways to draw connections between pieces of data.

The web article “A Report Has Come Here” by Klein (which was adapted from a presentation) is an enlightening glimpse at the positive uses that the digital humanities can have. The piece talks about the usage of computational finding connections in the documents of Thomas Jefferson to find out a man named James Hemings. Though it is pointed out that Hemings, who was a slave of Jefferson, isn’t mentioned by his full name once in the documents, through carefully making algorithm to tease out references to him in the vast array of documents, Klein was able to find parts of his life that weren’t clear before.

I thought the usage of secondary social connections to better understand the way that Hemings fit into Jefferson’s life was novel, and very useful. I feel that this piece informatively shows the benefits that can be derived from the use of technology in the humanities.

This article tells a story that explains the issues of historical labor and how they can forget important people from historical archives or never talking about them with their voices. I found the whole process of developing a “ new set of critical practices “  that suggest that we should “learn to see shadows in the archives” interesting. And this article shows that as my classmate JH said this could be done using digital tools, to gain knowledge about someone or something that is absent in the archival record. Also, another point made in the text that I found important was that “ no piece of writing exist alone. Rather, all texts are bound up in a set of larger social and cultural networks “. It makes me more aware when looking through data or when referencing to it.

In a previous post, a peer wrote that “topic modeling extends beyond the capacities of humans and opens new doors of understanding.” They said so in the context of approaching data pulled from topic modeling with caution, as it does not necessarily outweigh “the interpretive capacities of human scholars.” http://courses.shroutdocs.org/dcs104-fall2018/2018/10/25/the-digital-humanities-contribution-to-topic-modeling/  In contrast to this sentiment, “A Report has Come Here” sheds light not on what analysis of digital humanities cannot do, but on what it can. What we know off history is transmitted either orally or, more concretely, form documentation. Given that the people doing the documenting were often literate and upper class white men, quite a few voices (slaves, the poor, women, slaves etc) got left out along the way. Not only were their voices omitted, but what records we do  have are what was said about them by the white men. This lack of data makes the small traces of these people that much more important. Whereas approaching all the texts of history manually would be akin to searching for a needle in a haystack, Klein demonstrates how text analysis and visualization “offer some acknowledgment of the lives and stories that will forever remain unknown… challenges us to make the untold storied that we detect- those we might otherwise pass over- instead expand in our eyes with significance and meaning.”

The article, “A Report has Come Here,” not only explores the ways in which data can be missed, but also how data can be retrieved using digital tools. Through the use of a historical character, James Hemings, a slave of Thomas Jefferson, the author shows how we can use digital tools to gain knowledge about someone or something that is absent in the archival record. James Hemings was close to Thomas Jefferson, but when searching his name in The Papers of Thomas Jefferson, no results surface. This is because Jefferson never wrote to Hemings due to his slave title. Because of this, James Hemings could have easily been forgotten in history, but thanks to various digital techniques, information regarding Hemings could be uncovered. Reading about this one recovery of historical information makes me think about the millions of other people in history who have yet to be discovered and studied. Thousands of women and people of color has been ignored throughout history, and this development of digital tools brings the opportunity for them to be re-discovered. Similar to one of my classmates who also wrote about this article, I was intrigued by the idea that a lack of information on a person does not mean that story must remain unknown. As we become more and more developed in the digital age, we will be able to discover information that we once thought was lost.

In A Report Has Come Here, the author of this piece demonstrates his/her findings when extracting data from historical documents surrounding Thomas Jefferson’s personal chef, James Hemings. This article made me think about how this data was collected and the difficulty that comes with combing through historical documents years before a digitized society. I can only wonder how researchers were able to digitize all of this information from written text considering the number of documents that probably exist. Another piece of information from the article that I found extremely interesting was the fact that researchers were able to discover nicknames that Hemings was called by during his time in France. While impressive, this piece also made me consider the process in which researchers went about going through this data. I found that BL’s comment about using the individuals’ biographical information to be insightful when thinking about this question, “Using biographical data would make sense under these circumstances, as there aren’t many clear indicators of social interactions in more historical time periods that would provide enough data points…” This information speaks to how valuable text analysis can be in terms of discovering data that is present in between the lines of these historical texts.

An article expresses how topic modeling and text mining can make discoveries of the past. In this article using textual data and the text mining of multiple journals, essays, and letters, the researchers found the fascinating story of James Hemings.  Jefferson’s servant cook’s story is a story that would’ve been found without the help of text-mining. The lack of using his name, his outstanding skills and significance to Jefferson in literature made it impossible for historians to recognize the importance of Hemings. But thanks to text-mining, these researchers found patterns and consistencies of hundreds of letters and journals which lead them to the story of Jefferson’s cook. The article states: “Its exhilarating to think of the many ways in which digital tools might transform the archive of American slavery— pushing forward theories about the archive, arguments about its contents, and new forms of criticism that illuminate the past and inform the present.” Especially with suppressed groups throughout history, text-mining may be a way for us to dig out the ignored past of people.  A study in the “Digital Humanities”, too, focused on how social networks in texts could help us find relationships within countries — specifically Britain. But just like the Hemings article, biases in literature contribute to the meddling of data. The undermining of an individual based on their race, gender and religion, present in the 17th and 18th century, would heavily impact the results of the study. In recognizing this, the study stated: “A bias towards men is a known issue in existing historiography; this bias is neither confined to the ODNB nor particularly surprising. However, transforming textual secondary sources into visual representations allows for more purposeful “critical scrutiny of what is known, how, and by whom”. In response to last weeks readings, RF stated that “in some cases, the debate surrounding topic models is too concerned with the success of the algorithm itself opposed to the human space that the algorithm is working in”. In this, he means that the field of algorithms and the humanities are still rather polarized. As researchers in the humanities become more accustomed to the use of data analysis and text-mining,  society becomes a more connected and organized system.

The Six Degrees of Francis Bacon was a very fascinating analysis of relationships from 1500 to 1700.  The authors showed that people who have similar links tend to have the same number of mentions. For example, assume I was mentioned in a history book by a professor.  However, the professor also mentioned another student in section B. I may not know the other student at all, but that person can be a good indicator for number of mentions for myself in a history book.  This took some very advanced concepts to show and I am curious to see if we can explore those further in class.

This article highlights some of the really interesting use cases of machine learning for large (65 million word) data sets. This analysis would not be possible without the machine learning.

I believe this article relates closely to quantitative linguistics referred to in Sentiment Analysis and Subjectivity. As an expansion,I would be very curious if one could separate a “likability” for each person in the history books based on positive language as well.

After reading Why Topic Modeling is important by JM, I believe another expansion of the data set would be the tone women and gender are mentioned over time. I would be interested to see the progression of language for this topic.