Select Page

 Topic Modeling El Diario de la Gente (1972-1983):
Following the Relations between the Chicano Student Movement and the University of Colorado Administration

By Eva Danayanti (Journalism) and Juan Manuel García Fernández (Spanish & Portuguese Studies)


In this work, we applied Text Analysis as a method for examining El Diario de la Gente (1972-1983), a student newspaper created by the community of Chicanx students at the University of Colorado Boulder. Considering the wide range of topics that were covered throughout the years, including, for instance, international politics in Latin American or the resolutions of different courts on affirmative action cases, we use the topic modeling tool MALLET to examine how relevant the specific problems that these students had with the university administration were within the publication, as we believe it would be central to the student newspaper. Likewise, with Voyant, we analyze how the different events that took place while El Diario was published, such as the financial aid problems of 1975, affected its content throughout the years. Thus, this study offers a new instance of the Chicanx movement by presenting and defining the connection between the concerns and interests of the El Diario editors and the history of the Chicanx community during the 1970s and early 1980s.

Chicanx students and movement during the 1970s

Examining the experience of Chicano students in higher education institutions has been fundamental in those academic studies that have tried to explain the state and development of the Chicano community in the United States. As Vincent Tinto argues, the relationship between the individual and the institution administration was the key factor in which the student’s persistence at the university was funded. More concretely, other scholars manifest that the lack of representation of Chicano history in the academic curriculum as well as the lack of Chicano professors on campus are the main impediments to the development of these students (Carlos Arce 1978; Ronald Lopez et al 1976; Patrick Velasques 1996). Regarding these issues, Alers-Montalvo examines how Chicano students had already identified them as the main problems for their education and describes the students’ attempts at institutional changes and at the design of a curriculum that developed chicano identity (6).

All these historical issues analyzed by many scholars are also covered in El Diario. Therefore, we can see in the special edition that commemorates “Los Seis de Boulder”, published in September 2019, that the editors refer to how the original publication focused on information “especially important to Chicanx and other disenfranchised students” (1). In fact, the inaugural number of El Diario, a “Election Special” that covered student government elections, reflects how important having representation in the administration was for these students. All these issues relate, then, to the main topic and thesis of this work as we try to examine how the relation between the Chicano community and the university administration was covered in the student newspaper. Also, by studying El Diario, we hope to bring into academic research and conversations the contribution of these students to the Chicanx movement of the 1970s.

Digital Humanities Shifting the User’s Experience

Commonly, digital preservation faces a stand-still-and-die problem, since it only focuses on changing the platform instead of taking care of maintaining the data and accessibility (Kretzschmar and Potter 440). Digital Humanities allow scholars to change the approach on the digital preservation of material, which is not merely digitally available, but also present in a variety of different ways in order to preserve and keep the data updated. How do Digital Humanities maintain the data? According to Kretzschmar, technology in the digital era enables people to develop a new version to keep the data emerging continuously. Therefore, people need to collaborate to make it work.

This process has also been implemented in the digital analysis of El Diario. The different perspectives within academic conversations creates new broad ideas, which leads to innovation in elaborating the data. The use of Topic Modeling and digital technology helped us to examine this newspaper and to define the content through computing methods. This project offers a new perspective of El Diario and demonstrates that Digital Humanities projects guarantee the availability and originality of information.


This study analyzes the articles from El Diario Project, digitized by the Colorado Historical Newspapers, which were created as a corpus of plain text files by graduate students in DHUM 5000: Introduction to Digital Humanities: Movements, Methods, & Tools during Fall 2019 at University of Colorado Boulder. This corpus contains all the texts of the different issues of El Diario that were published between 1972 and 1983. Every file in this corpus is classified in one of four sections: “adverts”, “articles”, “creatives”, or “notices”. For this analysis, we are only using the section “articles” since we want to focus on how the relation between students and administration was reported by the editors and writers. The specific details about the data used in this work can be seen in Table 1.

Corpus Attribute Quantity
Years Covered 11
Issues 63
Articles 953
Total Words 450,195

 Table 1: Properties of the El Diario de la Gente Collections


We used the Text Analysis method to examine the corpus DHUM 5000: El Diario Project with the tools MALLET and Voyant. MALLET identifies patterns in a corpus of texts and groups words into topics, which can help us understand how important the relationship between students and the university administration was by comparing this topic with the rest. On the other hand, Voyant has several tools, of which we used “Corpus Collocates” and “Trends”.

After introducing the section of “articles” as the input to be analyzed by MALLET, we could choose the number of topics and words that we wanted to receive as results. We run the program many times with different settings. For instance, we tried to see if there was a difference between having 5 topics/10 words and having 35 topics/20 words. As the result of the analysis, MALLET provided a list of topics in no particular order from which we could select the topics related to our project. We also had to introduce in the settings of the application those frequent words (articles, prepositions, etc.) in Spanish so that they did not appear in the topics. Finally, we also explored the list that MALLET creates of all articles in order of significance for every topic.

However, although MALLET was the most appropriate tool to help us understand the relevance of the relations between students and the administration, this program presented some limitations when trying to analyze the change of the content over the years because it does not present the list of topics in order. For that reason, we decided to use Voyant, which does create a list of the most used words with “Corpus Collocates”.

With this last tool, we started by classifying the corpus per year of publication, then run the group of articles for each year separately with the goal of identifying the general topics of El Diario. Then we selected the top 20 words and assessed their connection to the articles to determine the most critical topics for every year.


For the first part of the project in which we examine the relevance of the topic within the selected section of the corpus, we ran MALLET many times with different settings to know if there was any difference between choosing a small or a large number of topics and words. Since we did not find any important difference, we decided to use just one set of results with 20 topics and 20 words in each. The final list can be seen in fig. 1, with the topics related to our main theme and thesis (5, 8, 17, and 18) highlighted in blue:

Figure 1: Full List of Topics with MALLET

As we can see, there are four topics connected to the Chicanx students’ experience in higher education. However, with a closer analysis of the most important articles of the first one of the topics (Topic 5 in fig. 2), we realized that this represented the legal cases of “affirmative action” that were being seen by different courts in the country and not the relations between the Chicanx students of UMAS and the University of Colorado administration specifically. Therefore, this topic was not considered for the rest of the project.


Topic 5 court law minority legal discrimination rights decision minorities school case admissions university bakke supreme civil action black white california filed

Figure 2: Topic 5

The other three university-related topics do represent the different issues that defined the relationship between UMAS and the administration. Thus, in Topic 8 (see fig. 3), we see how one of the main concerns for the Chicanx students was to ensure financial aid in order to being able to continue their education at the University of Colorado. In articles such as “Financial Aid Attacks E.O.P.”, from February 2, 1980, they explain how funding was being cut for work/study positions and minority programs.

Topic 8 board university chicano student minority committee chicanos asuc meeting members action boulder umas director president vote city position senate election

Figure 3: Topic 8

Another one of the topics related to our work is how UMAS students fought for Chicanx representation in academia (see fig. 4). In addition to working and demonstrating to help Chicanx professors to obtain their tenure, the student association also tried to be represented in the university curriculum and expand the number of courses on Chicanx culture and history and to consolidate a Chicanx program.

Topic 17 chicano studies music mexican professor mexico ramirez spanish american rivera el professors teatro group latin play george tenure department art

Figure 4: Topic 17

Finally, and perhaps the most important issue for being the central theme of the inaugural issue of El Diario was the one represented by Topic 18 (see fig. 5). This topic encapsulates how students struggled and tried to have representation in student governments to participate and defend their rights when creating policies. In the article “Minority Candidates Win Primary”, from October 10, 1972, Paul Mora describes how important winning this election was for every minority group on campus and how having representation in the student government was a pivotal change for the tactics of UMAS.

Topic 18 students umas student program university summer eop financial aid chicano work campus year study office colorado education semester american organization

Figure 5: Topic 18

 Finally, and perhaps the most important issue for being the central theme of the inaugural issue of El Diario was the one represented by Topic 18 (see fig. 5). This topic encapsulates how students struggled and tried to have representation in student governments to participate and defend their rights when creating policies. In the article “Minority Candidates Win Primary”, from October 10, 1972, Paul Mora describes how important winning this election was for every minority group on campus and how having representation in the student government was a pivotal change for the tactics of UMAS.

With these results provided by MALLET, we can attest how these three main topics can explain the relationship between the Chicanx students and the University of Colorado administration and how they compare to the rest of issues and concerns reported in El Diario.

For the second part of our project, the evolution and change of the content of the newspaper over time can be better explained by using Voyant, as we can see in Table 2. Furthermore, based on the list of words of each topic and the articles to which Voyant connected them, we provide an explanation or context for each topic.

Year Topics
1972 chicano; students; umas; chicanos; university; boycott; student; union; people; la; senate; program; children; minority; united; Colorado; community
1973 students; chicano; university; chicanos; umas; student; people; colorado; program; boulder; time; boycott; workers; vigil; board; minority
1974 chicano; people; students; boulder; university; program; umas; colorado; community; movement; time; new; board; school; state; education; support
1975 student; people; chicano; program; school; chicanos; community; student; committee; programs; new; years; university, bilingual; problems; education; support; need; sanchez
1976 chicano; people; said; chicanos; school; children; students; bill; public; years; community; struggle; student; government; tlatelolco; denver; numbers; colorado; bicultural; bilingual
1977 said; people; chicano; community; workers; students; colorado; program; denver; university; school; new; land; court; state; chicanos; minority; women; u.s; work
1978 people; u.s; chicano; students; puerto; said; law; time; school; colorado; year; police; workers; mexico; music; new; minority; student; years; percent
1979 coors; people; students; chicano; student; land; umas; chicanos; program; government; indian; workers; year; colorado; police; u.s; union; political; rights; time
1980 Chicano; students; people; chicanos; student; summer; conference; minority; financial; umas; work; lucero; american; la; aid; education; new; school; state; study
1981 people; umas; la; colorado; los; que; chicano; students; government; u.s; casa; en; mi; puerto; attack; el; leonard; rightstop; education; said
1983 student; people; students; e.o.p; chicano; chicanas; vida; become; french; leaders; lideres;salvador; struggle; cinco; mexico; minority; support; university; chicanos; education

Table 2: List of Main Topics Group per Year


As we can observe in these results, the content of El Diario and the interests of its editors changed over time due to the different events that were happening to the Chicano community. With this analysis of the complete corpus of articles from DHUM 5000: El Diario Project, we can see that El Diario moved from the inaugural issue focused on the student government elections to a much wider range of topics, with those corresponding to the relationship between the students and the administration becoming just a small part of the complete publication. Moreover, the study made with Voyant of the articles of each year explains this change in more detail. The fact that both tools connect the topics and most frequent words with the articles in the corpus also allows us to perform a close reading and to better understand all this information.

The method of Text Analysis not only helped us to explain how the relationship between the Chicano student movement and the University of Colorado administration as a topic in El Diario changed over time, but also to prove how this type of analysis can explain questions about this form of cultural production. Considering the characteristics of this study, in the future, it would also be useful to continue with a sentiment analysis. Those new results could provide another perspective to understand the issues and conditions of the publication of El Diario de la Gente.


Alers-Montalvo, Manuel. “Universities and the Chicano Student: An Assessment.” Annual Conference of the Western Social Science Association, Apr. 28 – May 1 1976, Tempe, AZ, Conference Presentation.

Arce, Carlos. “Chicano Participation in Academe: A Case of Academic Colonialism.” Grito del Sol: A Chicano Quarterly, vol. 3, 1978, pp. 75-104.

“DHUM 5000: El Diario Project.” OSF, 14 Nov. 2019,, Accessed 24 November 2019.

De los Santos, Alfredo, et al. “Chicano Students in Institutions of Higher Education: Access, Attrition, and Achievement.” Research Report Series, 1980,, Accessed 3 December 2019.

“History, Overview of El Diario.” El Diario de la Gente, 6 Sep. 2019, p. 1,, Accessed 2 December 2019.

Lopez, Ronald, et al. Chicanos in Higher Education: Status and Issues. UCLA Chicano Studies Center Publications, 1976.

Kretzschmar, William. A. and William Gray Potter. “Library collaboration with large digital humanities projects.” Literary & Linguistic Computing, vol. 25, no. 4, 2010, pp. 439–445.

Kretzschmar, William. A. and William Gray Potter. “Large-Scale Humanities Computing Projects: Snakes Eating Tails, or Every End is a New Beginning?” Digital Humanities Quarterly, vol. 3, no. 2, 2009,, Accessed 14 December 2019.

Tinto, Vincent. Leaving College: Rethinking the causes and curses of student attrition. University of Chicago Press, 1993.

Velasques, Patrick. “The Integration and Persistence of Chicano Students in Higher Education: Students and Institutional Characteristics.” Annual Meeting of the American Education Research Association, Apr. 8-13, 1996, New York, NY, Conference Presentation.

Von Destinon, Mark. “Chicano Student Persistence: The Effects of Integration and Involvement.” Internal Report Series, 1988,, Accessed 3 December 2019.