Sergio R. Coria

Climate patterns of political division units obtained using automatic classification trees

This article proposes a methodology to discover patterns in observed climatologic data, particularly temperatures and rainfall, in subnational political division units using an automatic classification algorithm (a decision tree produced by the C4.5 algorithm). Thus, the patterns represent classification trees, assuming that: (1) every political division unit contains at least one climatological station, and (2) the recording periods of the stations are relatively similar in duration and in their initial and ending years. A series of classification models are produced by using different subsets from an experimental dataset. This dataset contains information from 3606 climatological stations in Mexico with recording periods whose durations, initial and ending years are diverse. The target (dependent) variable in all these models is the name of the political unit (i.e., the state). The predictors are 36 monthly features per each climatological station: 12 features corresponding to a minimum temperature, 12 to a maximum temperature, and 12 to cumulative rainfall. The altitude feature is also used as one of the predictors, in addition to the other 36; however, it is used only to quantify its additional contribution to the modelling. The results show that classification trees are effective models for describing and representing non-trivial patterns to characterize the political division units based on their monthly temperatures and rainfalls. One of the remarkable findings is that the cumulative rainfall of May is the feature with highest discrimination capability to the characterization task, which is consistent with the theoretical background on Mexican climatology. In addition, classification trees offer higher expressivity to non-experts in machine learning.

CT4RDD: Classification trees for research on digital divide

Abstract This paper presents CT4RDD (classification trees for research on digital divide), a novel methodology for the quantitative analysis and modeling of the digital divide phenomenon with an approach of single country. It is inspired on the reputed Quinlan’s C4.5 algorithm to automatically produce classification trees, as implemented in Witten & Frank’s WEKA software toolkit. The methodology is created and evaluated on data from the 2010 Mexican Population and Housing Census that include a number of variables whose interactions involve aspects of the phenomenon; particularly, interactions among Internet service presence in households and a number of features regarding educational and economical levels, genders, ages, housing characteristics, ratios of indigenous population, etc. Discretization is used to represent percentages of presence of Internet in households of municipalities as a nominal target attribute to produce classification trees. Results suggest that the methodology can produce quantitative profiles that describe similarities and differences among a series of municipality classes that present different percentages of presence of Internet in households. The discovered profiles provide scholars, government officials and enterprise managers with valuable insight for research, planning and decision making.

An analysis of prosodic information for the recognition of dialogue acts in a multimodal corpus in Mexican Spanish

This paper presents empirical results of an analysis on the role of prosody in the recognition of dialogue acts and utterance mood in a practical dialogue corpus in Mexican Spanish. The work is configured as a series of machine-learning experimental conditions in which models are created by using intonational and other data as predictors and dialogue act tagging data as targets. We show that utterance mood can be predicted from intonational information, and that this mood information can then be used to recognize the dialogue act.

Climate data and and the Mexican standard on open data

This paper proposes recommendations on the adoption of the 2014 Mexican open data standard for using on climatological data for purposes of scientific research and public policy making in the climate and climate change fields in Mexico. The major benefit of its adoption is a higher accessibility to users who are not climatology or meteorology experts, such as scientists in other research areas, public policy makers, and private company strategists. Four specific sources on climate data from this country are addressed for these purposes.

MuniMex 1.0: a basic software interface for socio-demographic data of Mexican municipalities

This paper presents MuniMex 1.0, a basic and simple free software interface for selection and export of socio-demographic data of Mexican municipalities. MuniMex is aimed at facilitating scholars, government officials and company managers the usage of census municipal data for research, policy making and planning. Its database has been created using data from the 2010 Mexican census on population and housing, which are collected by the Mexican Institute on Statistics and Geography (INEGI). The original census data are construed by 191 variables corresponding to 2,456 municipalities. A collection of percentage variables have been computed from absolute frequency variables and are incorporated into the MuniMex database to offer the possibility to create analyses and models on a normalized basis. All these data can then be exported to Excel or CSV files to be exploited by using statistical or machine-learning tools.

Delta score : a novel simplified measurement for digital divide of cities

This work proposes Delta score a simplified nominal measurement for digital divide of cities. It is implemented as a concatenation of alphabetical scores that represent presence percentages of Internet, PC, fixed-line telephone and cell telephone in households of cities. Data from the 2010 Mexican Census on Population and Housing are used to create and evaluate this measurement. A proof of concept shows that the proposed measurement facilitates the creation of digital divide rankings and comparisons among cities within one single country. Also, this measurement suggests being useful for rankings and comparisons among cities of two or more countries. Potential incorporation of this score in inferential statistics is also suggested. Novelty and merits of this proposal are, among others: flexibility of the measurement discrete representation, and possibility to be used in inferential statistics; therefore, its usefulness for research purposes, public policy definition and private company planning is encouraging.